Clustering Lightened Deep Representation for Large Scale Face Identification

Size: px
Start display at page:

Download "Clustering Lightened Deep Representation for Large Scale Face Identification"

Transcription

1 Clustering Lightened Deep Representation for Large Scale Face Identification Shilun Lin Zhicheng Zhao Fei Su ABSTRACT On specific face dataset, such as the LFW benchmark, recent face recognition methods have achieved near perfect accuracy. However, the face identification is still a challenging task for a super large scale dataset, where a real application is urgently needed, thus Microsoft challenge of recognizing one million celebrities (MS-Celeb-1M) has attracted an increasing attention. In this paper, we propose a threestep strategy to address this problem. Firstly, based on a corss-domain face dataset, i.e., the CASIA-Web dataset, an efficient and deliberate face representation model with a Max-Feature-Map (MFM) activation function is trained to map raw images into the feature space quickly. Secondly, face representations with the same MID in MS-Celeb-1M are clustered into three subsets: a pure set, a hard set and a mess set. The cluster centers are used as gallery representations of the corresponding MID and this scheme reduces the impact of noisy images and the number of comparisons during the face matching. Finally, locality sensitive hashing (LSH) algorithm is applied to speed up the search of the nearest centroid. Experimental results show that our face CNN model can extract stable and discriminative face representations, and the proposed three-step strategy achieves a promising performance without any manual selection for the MS-Celeb-1M dataset. Furthermore, we find that via clustering a relatively pure set is kept by many MIDs in MS- Celeb-1M, which indicats this scheme is effective for cleaning a huge but mess dataset. 16], due to the publication of LFW [4], an extensively reported dataset for evaluation of face recognition algorithms. However, surpassing human recognition accuracy on LFW does not mean that the face recognition has been solved for the number of images in LFW is relatively small. Face i- dentification is still a challenging task for a super large scale dataset. In many real world applications, accurate identification at planetary scale is needed. i.e., in suspect searching, the face identification algorithm should find the suspect in the large scale gallery image set. Similarly, large scale robustness is also necessary in the field of mobile payment to ensure that other people can not use your account by their faces [5]. Recently, Microsoft is releasing MS-Celeb-1M [3], a large scale real world face image dataset to public, encouraging researchers to develop the best face recognition techniques to recognize one million people entities identified from Freebase. Its V1.0 version contains 10M celebrity face images for the top 100K celebrities, which can be used to train and evaluate both face identification and verification algorithms in a relatively large scale. In this paper, we propose a three-step strategy to address MS-Celeb-1M (V1.0 version) challenge of recognizing 100K celebrities in the real world, the flowchart is shown in Fig. 1. Keywords Large Scale Face Identification, Lightened Deep Representation, Clustering, Convolutional Neural Network 1. INTRODUCTION In the past few years, face recognition under uncontrolled environments becomes one of the most extensively research fields in computer vision [19, 20, 15, 17, 10, 8, 13, 2, 6, 14, Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from permissions@acm.org. ICC 17, March , Cambridge, United Kingdom c 2017 ACM. ISBN /17/03... $15.00 DOI: Figure 1: The basic idea of our proposed three-step strategy to MS-Celeb-1M challenge, including face representation extractor training, clustering in the feature space and closest centroid finding. To achieve ultimate accuracy, existing CNN based models tend to be deeper or use multiple local facial patch ensemble. The very deep model leads to a long computation time for representation extraction on CPU or GPU. And the appli-

2 cation of multiple facial patches requires much time and introduces uncertainty caused by automatic facial landmarks detection. While for large scale face recognition task, in addition to the time consuming and demand for a large number of computing resources in offline training, the time consuming of representation extraction and dimension of representation should be carefully considered. To obtain a small face representation extractor with fast speed of feature extraction and low-dimensional representation, widely used ReLU is replaced with Max-Feature-Map (MFM) which is proved to be effective [19]. Only a kind of aligned face patch extracted from CASIA-Webface [20] is applied as training data. There are two reasons for us not using MS-Celeb-1M dataset for training. On the one hand, this dataset is still relatively dirty at this stage and takes time to be cleaned. On the other hand, in practical application, it is difficult to cover all query identities in the training set. Our aim is to obtain a generalized model with good performance. The MS-Celeb-1M (V1.0 version) contains 8,456,240 of 99,892 MIDs. In such a large scale, it is not economical to compare query image with the entire dataset. The visualization of face representations obtained by the extractor provides a direct visual insight that through layer by layer abstraction, face representations of the same person tend to be similar, while there is a clear difference between representations of different person. According to this observation, K-means [7] is applied to face representations with the same MID in MS-Celeb-1M and three cluster centers (or less) are obtained as the gallery representations of the corresponding MID. The result of clustering shows face images corresponding to face representations of many MIDs were divided into three parts (pure set, hard set and mess set, the latter two do not necessarily exist). The pure set contains normal images of the person who appears most frequently in a MID folder. Faces in the hard set have variations in pose, illumination, or expression and a small amount of them do not belong to the person appears in pure set. Mess set is consists of those noisy images. Clustering in the feature space not only reduces the amount of computation required for the query phase, but also provides an effective preprocessing method for further data cleaning. Although the number of comparisons at the query phase is reduced by clustering, and face features are compact due to the MFM activation function. Searching for the nearest one from hundreds of thousands of gallery representations still limit the speed of our system. Locality-Sensitive Hashing (LSH) [12] is an effective method to deal with this issue. Through hashing similar gallery representations are mapped to the same bucket with high probability. During evaluation, LSH algorithm will map the query item to the bucket that contains similar gallery representations and consumes approximate O(1) time complexity to find the nearest one. 2. RELATED WORK 2.1 Data Set Face recognition history can be said to be the history of evolution of face database. Early face datasets, such as PIE [11], FERET [9], were almost collected under controlled environments. Very high performance is achieved on these ideal datasets through the efforts of many researchers. However, models learned from these datasets are difficult to generalize to practical applications, especially under the uncontrolled environments. So the interests of community gradually transferred from controlled environments to uncontrolled environments, and the publication of a milestone data-set, LFW [4], including 13,233 images of 5,749 identities, promotes the studies of unconstrained face recognition. Compared to previous datasets, the biggest difference of LFW is that the images are crawled from Internet rather than acquired under several pre-defined environments. Therefore, LFW has more variations in pose, illumination, expression, resolution, imaging device and these factors are combined together in random way. YTF [18] is based on the name list of LFW (1,595 identities) but it is created for video based face recognition. All the 3,425 videos in YTF were downloaded from YouTube. Because the videos on YouTube are highly compressed, the quality of the face snapshots are lower than LFW. Along with the development of deep learning, the scale of face database is also increasing. In the large scale public datasets, CASIA-WebFace [20] that includes about 500K photos of 10K celebrities crawled from the web is a great resource for training. Although the scale of CelebFaces [15] is relative smaller than CASIA-WebFace, it contains rich face attribute labels for face parsing. For large scale private datasets: Facebook s SFC [17] contains more then 4000 subjects and each subject has an average of 1000 images. Using SFC, [17] successfully learns an effective face representation robust to face variations in the wild. Google has access to massive photo collections, for example, they trained the FaceNet [10] on 200 Million photos of 8 Million people (and more recently on 500M of 10M) and won the outstanding performance in many face recognition tasks. The details of recent representative large scale face datasets are shown in Table. 1. Table 1: Current large scale face dataset. Dataset Identities Images Access WDRef [1] 2,995 99,773 Private CelebFace [15] 10, ,599 Public WebFace [20] 10, ,414 Public VGG Face [8] 2, M Public SFC [17] 4, M Private Google [10] 10M 500M Private 2.2 Deep Face Representation Learning Data and algorithm are two essential components for face recognition, especially for deep face representation learning. The publication of large scale web crawled dataset, promotes the studies of unconstrained face recognition. Several excellent face features were learned by different deep networks, and achieved high performance on LFW face verification task. Taigman et al. [17] proposed the DeepFace, which was a multi-class network trained to perform the face identification task on 4.4 million faces of over 4,000 identities. Through an ensemble of three networks using different alignments and color channels they obtained high accuracy approaching the human-level. Sun et al. [13] proposed to combine the identification and verification losses for reducing intra-personal variations while enlarging inter-personal differences during the training of DeepID2. They concatenated the features from 25 of such networks, each operating on a different face patch, and then PCA was applied to get

3 the compact face representation. Schroff et al. [10] presented a system, called FaceNet, which directly learned a mapping from face images to a compact Euclidean space with million training face thumbnails consisting of about 8 million different identities. All groups mentioned above surpassed human s performance and achieved near perfect results on the LFW benchmark. However, face recognition is far from being solved. Many applications require accurate identification at planetary scale like finding the best matching face in a database including billions of people while LFW includes only 13K photos of 5K people. The MS-Celeb-1M (V1.0 version) contains 8,456,240 of 99,892 MIDs. Using the entire MS-Celeb-1M dataset as gallery set may not be appropriate. On the one hand, the computation and storage overhead is relatively large, on the other hand, there are many noisy images in a MID folder and calculating the distance between them and query image is not necessary. In fact, through layer by layer abstraction (Fig. 3), face representation has a high distinguishability (intuitive visualization results will be given in section 4) which provides a good basis for clustering. So K-means algorithm is applied to face representations with the same MID in MS-Celeb-1M and three cluster centers (or less) are gained as the gallery representations of corresponding MID. During querying, only distances between all cluster centers and query image need to be calculated. Interestingly, in the absence of any supervisory information, pictures in a MID folder are automatically divided into different categories (pure, hard and mess, the latter two do not necessarily exist) which provides an effective preprocessing method for the follow-up database cleaning. 3. PROPOSED METHOD Since face recognition involves small inter-personal variations and large intra-personal variations, how to learn discriminative face representation narrowing the intra-personal distance and enlarging the inter-personal gap is always a key topic. Deep face representation has made remarkable breakthroughs in this field and been widely used. In the large scale face recognition, time consumption of feature extraction and overhead of feature storage should not be overlooked. Max- Feature-Map activation function proposed in [19] is advantageous to learn a CNN model with small size, fast speed of feature extraction and compact representation. As shown in Fig. 2, the output of MFM activation is the maximum between two convolution feature map candidate nodes. This operation selects more notable and discriminative nodes in both convolution and fully connected layers and makes the model lightened. Details of network architecture is given in Fig. 3. MFM instead of ReLU is utilized after convolutional layers and fully connected layer. Face representation is extracted from FC1 layer (after MFM activation). Figure 3: The flowchart of Transfer FaceNet. Figure 2: Principle of the Max-Feature-Map activation function. To further speed up our system, Locality-Sensitive Hashing (LSH) is utilized in the final query phase. Through hash similar cluster centers are mapped to the same bucket with high probability. During evaluation, LSH algorithm will map the query item to the bucket that contains similar gallery representations and consumes approximate O(1) time complexity to find the nearest one. 4. EXPERIMENTAL RESULTS 4.1 Face Representation Extractor In our experiments, model training is based on the open source deep learning framework Caffe [10]. Training samples for the face representation extractor are gray-scale aligned (using five facial landmarks) face images. And training samples are cropped into randomly and mirrored for data augmentation. 60% dropout is used to avoid overfitting on fully connected layers. The learning rate is set to 1e-3 initially and reduced to 1e-5 during learning. Fig. 4 shows feature maps from the Conv4b layer of the trained

4 which implies this scheme is effective for cleaning huge but mess data. Our results of clustering in the feature space provides guidance for further data cleaning which is helpful to obtain a relatively clean and large scale dataset to be used to train a more powerful face representation extractor. Figure 5: Clustering results of MID m.0b3q8k (top) and m.0cz96px (bottom) in MS-Celeb-1M (V1). Figure 4: Visualization of the first 36 feature maps produced by the Conv4b layer of face representation extractor on images of Zhiling Lin (a,b,left) and X- iang Chen (c,d,right). Best viewed in color. face representation extractor. We can see that the response of face concepts like mouth and eyes is visible which can provide discriminative information for face recognition. For example, in our daily life, we intuitively use concepts like big eyes and high nose to distinguish different people. Comparing feature maps of same persons (a vs. b, feature maps in the red boxes for instance) in Fig. 4, we can find that the intra-personal variations of feature maps produced by higher layer of the face representation extractor is small. And the feature maps of two different persons have a significant difference (a vs. c, feature maps in the red and green boxes). This characteristic of the face representation provides a good foundation for the further clustering. 4.2 Clustering in the Feature Space With the purpose of reducing the number of comparisons during evaluation and excluding the impact of noise images on identification performance, K-means algorithm is applied to face representations with the same MID in MS-Celeb-1M and three cluster centers (or less) are gained as the gallery representations of corresponding MID. Some results of clustering are shown in Fig. 5. Images of MID m.0b3q8k (top) are divided into three sets including pure set, hard set and mess set as we described before. Hard set or mess set doesn t always exist, because images of some MID have been relatively pure. MID m.0cz96px (bottom) includes face images of many identities, and it is difficult to confirm which one is the main identity. We believe that images corresponding to such MID need to be re-collected. We find that via clustering a relatively pure set is kept by many MIDs in MS-Celeb-1M, 4.3 Performance In querying, corresponding MID of the nearest centroid is assigned to the query image. Introducing Locality-Sensitive Hashing (LSH) is effective to speed up the process of finding the closest centroid (from O(n) to approximate O(1) time complexity, n is the number of centroids). Because we emphasize on the generalization ability of our system on the large scale web-crawled face dataset, in the process of building our system and testing, neither MS-Celeb-1M (V1) is used for training, nor any artificial cleaning is applied to this dataset. Finally, 58.20% and 38.4% top1 identification rate is achieved on the MS-Celeb-1M (V1) random and hard dev set respectively. The 100K-list in the MS- Celeb-1M (V1) only covers about 75% of celebrities in the measurement set. So in the absence of any expansion of the database, the highest identification rate is 75%. 5. CONCLUSION AND FUTURE WORK This paper proposes a three-step strategy to construct a promising system for large scale automatic face identification by clustering lightened deep representation. We offer an intuitive visual interpretation to the discriminability of lightened deep representation. Face representations are clustered in the feature space based on this observation, which can reduce the impact of noise images mixed in each MID and the number of comparisons during matching. Benefit from the discriminable face representation, images of corresponding MID are divided into three set (or less) and most of MIDs contain a pure set of the main identity. Such automated processing will reduce the labor cost of further data cleaning. Moreover, a relatively clean dataset is essential for training a deep model with strong generalization ability. Exploring the appropriate number of cluster centers of each MID is one of the key points in our future work. How to achieve a good tradeoff between processing speed and accuracy is one of the issues to be solved in large scale face recognition system.

5 6. ACKNOWLEDGMENT This work is supported by Chinese National Natural Science Foundation ( , , ), Special Funds of Beijing Municipal Co-construction Project, and Beijing Key Lab of Network System and Network Culture. 7. REFERENCES [1] D. Chen, X. Cao, L. Wang, F. Wen, and J. Sun. Bayesian face revisited: A joint formulation. In Computer Vision ECCV 2012, pages Springer, [2] D. Chen, X. Cao, F. Wen, and J. Sun. Blessing of dimensionality: High-dimensional feature and its efficient compression for face verification. In Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, pages IEEE, [3] Y. Guo, L. Zhang, Y. Hu, X. He, and J. Gao. Ms-celeb-1m: Challenge of recognizing one million celebri-ties in the real world. [4] G. B. Huang, M. Ramesh, T. Berg, and E. Learned-Miller. Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Technical report, Technical Report 07-49, University of Massachusetts, Amherst, [5] I. Kemelmacher-Shlizerman, S. Seitz, D. Miller, and E. Brossard. The megaface benchmark: 1 million faces for recognition at scale. arxiv preprint arxiv: , [6] C. Lu and X. Tang. Surpassing human-level face verification performance on lfw with gaussianface. arxiv preprint arxiv: , [7] J. MacQueen et al. Some methods for classification and analysis of multivariate observations. In Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, volume 1, pages Oakland, CA, USA., [8] O. M. Parkhi, A. Vedaldi, and A. Zisserman. Deep face recognition. In British Machine Vision Conference, volume 1, page 6, [9] P. J. Phillips, H. Moon, S. Rizvi, P. J. Rauss, et al. The feret evaluation methodology for face-recognition algorithms. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 22(10): , [10] F. Schroff, D. Kalenichenko, and J. Philbin. Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages , [11] T. Sim, S. Baker, and M. Bsat. The cmu pose, illumination, and expression (pie) database. In Automatic Face and Gesture Recognition, Proceedings. Fifth IEEE International Conference on, pages IEEE, [12] M. Slaney and M. Casey. Locality-sensitive hashing for finding nearest neighbors [lecture notes]. IEEE Signal Processing Magazine, 25(2): , [13] Y. Sun, Y. Chen, X. Wang, and X. Tang. Deep learning face representation by joint identification-verification. In Advances in Neural Information Processing Systems, pages , [14] Y. Sun, X. Wang, and X. Tang. Hybrid deep learning for face verification. In Computer Vision (ICCV), 2013 IEEE International Conference on, pages IEEE, [15] Y. Sun, X. Wang, and X. Tang. Deep learning face representation from predicting 10,000 classes. In Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on, pages IEEE, [16] Y. Sun, X. Wang, and X. Tang. Deeply learned face representations are sparse, selective, and robust. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages , [17] Y. Taigman, M. Yang, M. Ranzato, and L. Wolf. Deepface: Closing the gap to human-level performance in face verification. In Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on, pages IEEE, [18] L. Wolf, T. Hassner, and I. Maoz. Face recognition in unconstrained videos with matched background similarity. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pages IEEE, [19] X. Wu, R. He, and Z. Sun. A lightened cnn for deep face representation. arxiv preprint arxiv: , [20] D. Yi, Z. Lei, S. Liao, and S. Z. Li. Learning face representation from scratch. arxiv preprint arxiv: , 2014.

Robust Face Recognition Based on Convolutional Neural Network

Robust Face Recognition Based on Convolutional Neural Network 2017 2nd International Conference on Manufacturing Science and Information Engineering (ICMSIE 2017) ISBN: 978-1-60595-516-2 Robust Face Recognition Based on Convolutional Neural Network Ying Xu, Hui Ma,

More information

Face Recognition via Active Annotation and Learning

Face Recognition via Active Annotation and Learning Face Recognition via Active Annotation and Learning Hao Ye 1, Weiyuan Shao 1, Hong Wang 1, Jianqi Ma 2, Li Wang 2, Yingbin Zheng 1, Xiangyang Xue 2 1 Shanghai Advanced Research Institute, Chinese Academy

More information

Face Recognition A Deep Learning Approach

Face Recognition A Deep Learning Approach Face Recognition A Deep Learning Approach Lihi Shiloh Tal Perl Deep Learning Seminar 2 Outline What about Cat recognition? Classical face recognition Modern face recognition DeepFace FaceNet Comparison

More information

FaceNet. Florian Schroff, Dmitry Kalenichenko, James Philbin Google Inc. Presentation by Ignacio Aranguren and Rahul Rana

FaceNet. Florian Schroff, Dmitry Kalenichenko, James Philbin Google Inc. Presentation by Ignacio Aranguren and Rahul Rana FaceNet Florian Schroff, Dmitry Kalenichenko, James Philbin Google Inc. Presentation by Ignacio Aranguren and Rahul Rana Introduction FaceNet learns a mapping from face images to a compact Euclidean Space

More information

Deep Learning for Face Recognition. Xiaogang Wang Department of Electronic Engineering, The Chinese University of Hong Kong

Deep Learning for Face Recognition. Xiaogang Wang Department of Electronic Engineering, The Chinese University of Hong Kong Deep Learning for Face Recognition Xiaogang Wang Department of Electronic Engineering, The Chinese University of Hong Kong Deep Learning Results on LFW Method Accuracy (%) # points # training images Huang

More information

arxiv: v1 [cs.cv] 9 Jun 2016

arxiv: v1 [cs.cv] 9 Jun 2016 A Comprehensive Analysis of Deep Learning Based Representation for Face Recognition arxiv:1606.02894v1 [cs.cv] 9 Jun 2016 Mostafa Mehdipour Ghazi Faculty of Engineering and Natural Sciences Sabanci University,

More information

arxiv: v1 [cs.cv] 1 Jun 2018

arxiv: v1 [cs.cv] 1 Jun 2018 Accurate and Efficient Similarity Search for Large Scale Face Recognition Ce Qi BUPT Zhizhong Liu BUPT Fei Su BUPT arxiv:1806.00365v1 [cs.cv] 1 Jun 2018 Abstract Face verification is a relatively easy

More information

DeepFace: Closing the Gap to Human-Level Performance in Face Verification

DeepFace: Closing the Gap to Human-Level Performance in Face Verification DeepFace: Closing the Gap to Human-Level Performance in Face Verification Report on the paper Artem Komarichev February 7, 2016 Outline New alignment technique New DNN architecture New large dataset with

More information

Improving Face Recognition by Exploring Local Features with Visual Attention

Improving Face Recognition by Exploring Local Features with Visual Attention Improving Face Recognition by Exploring Local Features with Visual Attention Yichun Shi and Anil K. Jain Michigan State University Difficulties of Face Recognition Large variations in unconstrained face

More information

arxiv: v1 [cs.cv] 4 Nov 2016

arxiv: v1 [cs.cv] 4 Nov 2016 UMDFaces: An Annotated Face Dataset for Training Deep Networks Ankan Bansal Anirudh Nanduri Rajeev Ranjan Carlos D. Castillo Rama Chellappa University of Maryland, College Park {ankan,snanduri,rranjan1,carlos,rama}@umiacs.umd.edu

More information

SHIV SHAKTI International Journal in Multidisciplinary and Academic Research (SSIJMAR) Vol. 7, No. 2, April 2018 (ISSN )

SHIV SHAKTI International Journal in Multidisciplinary and Academic Research (SSIJMAR) Vol. 7, No. 2, April 2018 (ISSN ) SHIV SHAKTI International Journal in Multidisciplinary and Academic Research (SSIJMAR) Vol. 7, No. 2, April 2018 (ISSN 2278 5973) Facial Recognition Using Deep Learning Rajeshwar M, Sanjit Singh Chouhan,

More information

arxiv: v1 [cs.cv] 16 Nov 2015

arxiv: v1 [cs.cv] 16 Nov 2015 Coarse-to-fine Face Alignment with Multi-Scale Local Patch Regression Zhiao Huang hza@megvii.com Erjin Zhou zej@megvii.com Zhimin Cao czm@megvii.com arxiv:1511.04901v1 [cs.cv] 16 Nov 2015 Abstract Facial

More information

arxiv: v1 [cs.cv] 31 Jul 2018

arxiv: v1 [cs.cv] 31 Jul 2018 The Devil of Face Recognition is in the Noise Fei Wang 1[0000 0002 1024 5867], Liren Chen 2[0000 0003 0113 5233], Cheng Li 1[0000 0002 0892 4705], Shiyao Huang 1[0000 0002 5198 2492], Yanjie Chen 1[0000

More information

Face Recognition by Deep Learning - The Imbalance Problem

Face Recognition by Deep Learning - The Imbalance Problem Face Recognition by Deep Learning - The Imbalance Problem Chen-Change LOY MMLAB The Chinese University of Hong Kong Homepage: http://personal.ie.cuhk.edu.hk/~ccloy/ Twitter: https://twitter.com/ccloy CVPR

More information

arxiv: v4 [cs.cv] 30 May 2018

arxiv: v4 [cs.cv] 30 May 2018 Additive Margin Softmax for Face Verification Feng Wang UESTC feng.wff@gmail.com Weiyang Liu Georgia Tech wyliu@gatech.edu Haijun Liu UESTC haijun liu@26.com Jian Cheng UESTC chengjian@uestc.edu.cn arxiv:80.05599v4

More information

A Patch Strategy for Deep Face Recognition

A Patch Strategy for Deep Face Recognition A Patch Strategy for Deep Face Recognition Yanhong Zhang a, Kun Shang a, Jun Wang b, Nan Li a, Monica M.Y. Zhang c a Center for Applied Mathematics, Tianjin University, Tianjin 300072, P.R. China b School

More information

Deep Convolutional Neural Network using Triplet of Faces, Deep Ensemble, and Scorelevel Fusion for Face Recognition

Deep Convolutional Neural Network using Triplet of Faces, Deep Ensemble, and Scorelevel Fusion for Face Recognition IEEE 2017 Conference on Computer Vision and Pattern Recognition Deep Convolutional Neural Network using Triplet of Faces, Deep Ensemble, and Scorelevel Fusion for Face Recognition Bong-Nam Kang*, Yonghyun

More information

Large-scale Datasets: Faces with Partial Occlusions and Pose Variations in the Wild

Large-scale Datasets: Faces with Partial Occlusions and Pose Variations in the Wild Large-scale Datasets: Faces with Partial Occlusions and Pose Variations in the Wild Tarik Alafif, Zeyad Hailat, Melih Aslan and Xuewen Chen Computer Science Department, Wayne State University Detroit,

More information

High Performance Large Scale Face Recognition with Multi-Cognition Softmax and Feature Retrieval

High Performance Large Scale Face Recognition with Multi-Cognition Softmax and Feature Retrieval High Performance Large Scale Face Recognition with Multi-Cognition Softmax and Feature Retrieval Yan Xu* 1 Yu Cheng* 1 Jian Zhao 2 Zhecan Wang 3 Lin Xiong 1 Karlekar Jayashree 1 Hajime Tamura 4 Tomoyuki

More information

MobileFaceNets: Efficient CNNs for Accurate Real- Time Face Verification on Mobile Devices

MobileFaceNets: Efficient CNNs for Accurate Real- Time Face Verification on Mobile Devices MobileFaceNets: Efficient CNNs for Accurate Real- Time Face Verification on Mobile Devices Sheng Chen 1,2, Yang Liu 2, Xiang Gao 2, and Zhen Han 1 1 School of Computer and Information Technology, Beijing

More information

Recursive Spatial Transformer (ReST) for Alignment-Free Face Recognition

Recursive Spatial Transformer (ReST) for Alignment-Free Face Recognition Recursive Spatial Transformer (ReST) for Alignment-Free Face Recognition Wanglong Wu 1,2 Meina Kan 1,3 Xin Liu 1,2 Yi Yang 4 Shiguang Shan 1,3 Xilin Chen 1 1 Key Lab of Intelligent Information Processing

More information

arxiv: v1 [cs.cv] 31 Mar 2017

arxiv: v1 [cs.cv] 31 Mar 2017 End-to-End Spatial Transform Face Detection and Recognition Liying Chi Zhejiang University charrin0531@gmail.com Hongxin Zhang Zhejiang University zhx@cad.zju.edu.cn Mingxiu Chen Rokid.inc cmxnono@rokid.com

More information

Improving Face Recognition by Exploring Local Features with Visual Attention

Improving Face Recognition by Exploring Local Features with Visual Attention Improving Face Recognition by Exploring Local Features with Visual Attention Yichun Shi and Anil K. Jain Michigan State University East Lansing, Michigan, USA shiyichu@msu.edu, jain@cse.msu.edu Abstract

More information

Face Alignment Under Various Poses and Expressions

Face Alignment Under Various Poses and Expressions Face Alignment Under Various Poses and Expressions Shengjun Xin and Haizhou Ai Computer Science and Technology Department, Tsinghua University, Beijing 100084, China ahz@mail.tsinghua.edu.cn Abstract.

More information

Learning to Recognize Faces in Realistic Conditions

Learning to Recognize Faces in Realistic Conditions 000 001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050

More information

Learning Invariant Deep Representation for NIR-VIS Face Recognition

Learning Invariant Deep Representation for NIR-VIS Face Recognition Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17) Learning Invariant Deep Representation for NIR-VIS Face Recognition Ran He, Xiang Wu, Zhenan Sun, Tieniu Tan National

More information

Deep Learning for Vision

Deep Learning for Vision Deep Learning for Vision Presented by Kevin Matzen Quick Intro - DNN Feed-forward Sparse connectivity (layer to layer) Different layer types Recently popularized for vision [Krizhevsky, et. al. NIPS 2012]

More information

Residual vs. Inception vs. Classical Networks for Low-Resolution Face Recognition

Residual vs. Inception vs. Classical Networks for Low-Resolution Face Recognition Residual vs. Inception vs. Classical Networks for Low-Resolution Face Recognition Christian Herrmann 1,2, Dieter Willersinn 2, and Jürgen Beyerer 1,2 1 Vision and Fusion Lab, Karlsruhe Institute of Technology

More information

Deep Face Recognition. Nathan Sun

Deep Face Recognition. Nathan Sun Deep Face Recognition Nathan Sun Why Facial Recognition? Picture ID or video tracking Higher Security for Facial Recognition Software Immensely useful to police in tracking suspects Your face will be an

More information

arxiv: v1 [cs.cv] 4 Aug 2011

arxiv: v1 [cs.cv] 4 Aug 2011 arxiv:1108.1122v1 [cs.cv] 4 Aug 2011 Leveraging Billions of Faces to Overcome Performance Barriers in Unconstrained Face Recognition Yaniv Taigman and Lior Wolf face.com {yaniv, wolf}@face.com Abstract

More information

arxiv: v4 [cs.cv] 14 Nov 2016

arxiv: v4 [cs.cv] 14 Nov 2016 Pose-Selective Max Pooling for Measuring Similarity Xiang Xiang 1 and Trac D. Tran 2 arxiv:1609.07042v4 [cs.cv] 14 Nov 2016 1 Dept. of Computer Science 2 Dept. of Electrical & Computer Engineering Johns

More information

An Associate-Predict Model for Face Recognition FIPA Seminar WS 2011/2012

An Associate-Predict Model for Face Recognition FIPA Seminar WS 2011/2012 An Associate-Predict Model for Face Recognition FIPA Seminar WS 2011/2012, 19.01.2012 INSTITUTE FOR ANTHROPOMATICS, FACIAL IMAGE PROCESSING AND ANALYSIS YIG University of the State of Baden-Wuerttemberg

More information

Hybrid Deep Learning for Face Verification

Hybrid Deep Learning for Face Verification 2013 IEEE International Conference on Computer Vision Hybrid Deep Learning for Face Verification Yi Sun 1 Xiaogang Wang 2,3 Xiaoou Tang 1,3 1 Department of Information Engineering, The Chinese University

More information

Cost-alleviative Learning for Deep Convolutional Neural Network-based Facial Part Labeling

Cost-alleviative Learning for Deep Convolutional Neural Network-based Facial Part Labeling [DOI: 10.2197/ipsjtcva.7.99] Express Paper Cost-alleviative Learning for Deep Convolutional Neural Network-based Facial Part Labeling Takayoshi Yamashita 1,a) Takaya Nakamura 1 Hiroshi Fukui 1,b) Yuji

More information

Boosting Sex Identification Performance

Boosting Sex Identification Performance Boosting Sex Identification Performance Shumeet Baluja, 2 Henry Rowley shumeet@google.com har@google.com Google, Inc. 2 Carnegie Mellon University, Computer Science Department Abstract This paper presents

More information

Supplementary Material: Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos

Supplementary Material: Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos Supplementary Material: Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos Kihyuk Sohn 1 Sifei Liu 2 Guangyu Zhong 3 Xiang Yu 1 Ming-Hsuan Yang 2 Manmohan Chandraker 1,4 1 NEC Labs

More information

SphereFace: Deep Hypersphere Embedding for Face Recognition

SphereFace: Deep Hypersphere Embedding for Face Recognition SphereFace: Deep Hypersphere Embedding for Face Recognition Weiyang Liu Yandong Wen Zhiding Yu Ming Li 3 Bhiksha Raj Le Song Georgia Institute of Technology Carnegie Mellon University 3 Sun Yat-Sen University

More information

FISHER VECTOR ENCODED DEEP CONVOLUTIONAL FEATURES FOR UNCONSTRAINED FACE VERIFICATION

FISHER VECTOR ENCODED DEEP CONVOLUTIONAL FEATURES FOR UNCONSTRAINED FACE VERIFICATION FISHER VECTOR ENCODED DEEP CONVOLUTIONAL FEATURES FOR UNCONSTRAINED FACE VERIFICATION Jun-Cheng Chen, Jingxiao Zheng, Vishal M. Patel 2, and Rama Chellappa. University of Maryland, College Par 2. Rutgers,

More information

Face Recognition with Contrastive Convolution

Face Recognition with Contrastive Convolution Face Recognition with Contrastive Convolution Chunrui Han 1,2[0000 0001 9725 280X], Shiguang Shan 1,3[0000 0002 8348 392X], Meina Kan 1,3[0000 0001 9483 875X], Shuzhe Wu 1,2[0000 0002 4455 4123], and Xilin

More information

arxiv: v1 [cs.cv] 12 Mar 2014

arxiv: v1 [cs.cv] 12 Mar 2014 Learning Deep Face Representation Haoqiang Fan Megvii Inc. fhq@megvii.com Zhimin Cao Megvii Inc. czm@megvii.com Yuning Jiang Megvii Inc. jyn@megvii.com Qi Yin Megvii Inc. yq@megvii.com arxiv:1403.2802v1

More information

The Analysis of Faces in Brains and Machines

The Analysis of Faces in Brains and Machines CS 332 Visual Processing in Computer and Biological Vision Systems The Analysis of Faces in Brains and Machines Paula Johnson Elizabeth Warren HMAX model Why is face analysis important? Remember/recognize

More information

Joint Unsupervised Learning of Deep Representations and Image Clusters Supplementary materials

Joint Unsupervised Learning of Deep Representations and Image Clusters Supplementary materials Joint Unsupervised Learning of Deep Representations and Image Clusters Supplementary materials Jianwei Yang, Devi Parikh, Dhruv Batra Virginia Tech {jw2yang, parikh, dbatra}@vt.edu Abstract This supplementary

More information

FACIAL POINT DETECTION BASED ON A CONVOLUTIONAL NEURAL NETWORK WITH OPTIMAL MINI-BATCH PROCEDURE. Chubu University 1200, Matsumoto-cho, Kasugai, AICHI

FACIAL POINT DETECTION BASED ON A CONVOLUTIONAL NEURAL NETWORK WITH OPTIMAL MINI-BATCH PROCEDURE. Chubu University 1200, Matsumoto-cho, Kasugai, AICHI FACIAL POINT DETECTION BASED ON A CONVOLUTIONAL NEURAL NETWORK WITH OPTIMAL MINI-BATCH PROCEDURE Masatoshi Kimura Takayoshi Yamashita Yu Yamauchi Hironobu Fuyoshi* Chubu University 1200, Matsumoto-cho,

More information

Kaggle Data Science Bowl 2017 Technical Report

Kaggle Data Science Bowl 2017 Technical Report Kaggle Data Science Bowl 2017 Technical Report qfpxfd Team May 11, 2017 1 Team Members Table 1: Team members Name E-Mail University Jia Ding dingjia@pku.edu.cn Peking University, Beijing, China Aoxue Li

More information

ROBUST PARTIAL FACE RECOGNITION USING INSTANCE-TO-CLASS DISTANCE

ROBUST PARTIAL FACE RECOGNITION USING INSTANCE-TO-CLASS DISTANCE ROBUST PARTIAL FACE RECOGNITION USING INSTANCE-TO-CLASS DISTANCE Junlin Hu 1, Jiwen Lu 2, and Yap-Peng Tan 1 1 School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore

More information

arxiv: v4 [cs.cv] 10 Jun 2018

arxiv: v4 [cs.cv] 10 Jun 2018 Enhancing Convolutional Neural Networks for Face Recognition with Occlusion Maps and Batch Triplet Loss Daniel Sáez Trigueros a,b, Li Meng a,, Margaret Hartnett b a School of Engineering and Technology,

More information

FACIAL POINT DETECTION USING CONVOLUTIONAL NEURAL NETWORK TRANSFERRED FROM A HETEROGENEOUS TASK

FACIAL POINT DETECTION USING CONVOLUTIONAL NEURAL NETWORK TRANSFERRED FROM A HETEROGENEOUS TASK FACIAL POINT DETECTION USING CONVOLUTIONAL NEURAL NETWORK TRANSFERRED FROM A HETEROGENEOUS TASK Takayoshi Yamashita* Taro Watasue** Yuji Yamauchi* Hironobu Fujiyoshi* *Chubu University, **Tome R&D 1200,

More information

Channel Locality Block: A Variant of Squeeze-and-Excitation

Channel Locality Block: A Variant of Squeeze-and-Excitation Channel Locality Block: A Variant of Squeeze-and-Excitation 1 st Huayu Li Northern Arizona University Flagstaff, United State Northern Arizona University hl459@nau.edu arxiv:1901.01493v1 [cs.lg] 6 Jan

More information

Investigating Nuisance Factors in Face Recognition with DCNN Representation

Investigating Nuisance Factors in Face Recognition with DCNN Representation Investigating Nuisance Factors in Face Recognition with DCNN Representation Claudio Ferrari, Giuseppe Lisanti, Stefano Berretti, Alberto Del Bimbo Media Integration and Communication Center (MICC) University

More information

arxiv: v1 [cs.mm] 12 Jan 2016

arxiv: v1 [cs.mm] 12 Jan 2016 Learning Subclass Representations for Visually-varied Image Classification Xinchao Li, Peng Xu, Yue Shi, Martha Larson, Alan Hanjalic Multimedia Information Retrieval Lab, Delft University of Technology

More information

LOCAL APPEARANCE BASED FACE RECOGNITION USING DISCRETE COSINE TRANSFORM

LOCAL APPEARANCE BASED FACE RECOGNITION USING DISCRETE COSINE TRANSFORM LOCAL APPEARANCE BASED FACE RECOGNITION USING DISCRETE COSINE TRANSFORM Hazim Kemal Ekenel, Rainer Stiefelhagen Interactive Systems Labs, University of Karlsruhe Am Fasanengarten 5, 76131, Karlsruhe, Germany

More information

Minimum Margin Loss for Deep Face Recognition

Minimum Margin Loss for Deep Face Recognition JOURNAL OF L A TEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 1 Minimum Margin Loss for Deep Face Recognition Xin Wei, Student Member, IEEE, Hui Wang, Member, IEEE, Bryan Scotney, and Huan Wan arxiv:1805.06741v4

More information

Improved Face Detection and Alignment using Cascade Deep Convolutional Network

Improved Face Detection and Alignment using Cascade Deep Convolutional Network Improved Face Detection and Alignment using Cascade Deep Convolutional Network Weilin Cong, Sanyuan Zhao, Hui Tian, and Jianbing Shen Beijing Key Laboratory of Intelligent Information Technology, School

More information

Deep Fisher Faces. 1 Introduction. Harald Hanselmann

Deep Fisher Faces. 1 Introduction. Harald Hanselmann HANSELMANN, YAN, NEY: DEEP FISHER FACES 1 Deep Fisher Faces Harald Hanselmann hanselmann@cs.rwth-aachen.de Shen Yan shen.yan@rwth-aachen.de Hermann Ney ney@cs.rwth-aachen.de Human Language Technology and

More information

arxiv: v1 [cs.cv] 6 Nov 2016

arxiv: v1 [cs.cv] 6 Nov 2016 Deep Convolutional Neural Network Features and the Original Image Connor J. Parde 1 and Carlos Castillo 2 and Matthew Q. Hill 1 and Y. Ivette Colon 1 and Swami Sankaranarayanan 2 and Jun-Cheng Chen 2 and

More information

An Exploration of Computer Vision Techniques for Bird Species Classification

An Exploration of Computer Vision Techniques for Bird Species Classification An Exploration of Computer Vision Techniques for Bird Species Classification Anne L. Alter, Karen M. Wang December 15, 2017 Abstract Bird classification, a fine-grained categorization task, is a complex

More information

FACE recognition has been one of the most extensively. Robust Face Recognition via Multimodal Deep Face Representation

FACE recognition has been one of the most extensively. Robust Face Recognition via Multimodal Deep Face Representation TO APPEAR IN IEEE TRANSACTIONS ON MULTIMEDIA, 2015 1 Robust Face Recognition via Multimodal Deep Face Representation Changxing Ding, Student Member, IEEE, Dacheng Tao, Fellow, IEEE arxiv:1509.00244v1 [cs.cv]

More information

arxiv: v1 [cs.cv] 15 Nov 2018

arxiv: v1 [cs.cv] 15 Nov 2018 Pairwise Relational Networks using Local Appearance Features for Face Recognition arxiv:1811.06405v1 [cs.cv] 15 Nov 2018 Bong-Nam Kang Department of Creative IT Engineering POSTECH, Korea bnkang@postech.ac.kr

More information

arxiv: v1 [cs.cv] 7 Dec 2015

arxiv: v1 [cs.cv] 7 Dec 2015 Sparsifying Neural Network Connections for Face Recognition Yi Sun 1 Xiaogang Wang 2,4 Xiaoou Tang 3,4 1 SenseTime Group 2 Department of Electronic Engineering, The Chinese University of Hong Kong 3 Department

More information

arxiv: v1 [cs.cv] 19 May 2018

arxiv: v1 [cs.cv] 19 May 2018 Long-term face tracking in the wild using deep learning Kunlei Zhang a, Elaheh Barati a, Elaheh Rashedi a,, Xue-wen Chen a a Dept. of Computer Science, Wayne State University, Detroit, MI arxiv:1805.07646v1

More information

Face Recognition At-a-Distance Based on Sparse-Stereo Reconstruction

Face Recognition At-a-Distance Based on Sparse-Stereo Reconstruction Face Recognition At-a-Distance Based on Sparse-Stereo Reconstruction Ham Rara, Shireen Elhabian, Asem Ali University of Louisville Louisville, KY {hmrara01,syelha01,amali003}@louisville.edu Mike Miller,

More information

Hybrid Deep Learning for Face Verification. Yi Sun, Xiaogang Wang, Member, IEEE, and Xiaoou Tang, Fellow, IEEE

Hybrid Deep Learning for Face Verification. Yi Sun, Xiaogang Wang, Member, IEEE, and Xiaoou Tang, Fellow, IEEE 1 Hybrid Deep Learning for Face Verification Yi Sun, Xiaogang Wang, Member, IEEE, and Xiaoou Tang, Fellow, IEEE Abstract This paper proposes a hybrid convolutional network (ConvNet)-Restricted Boltzmann

More information

Boosting face recognition via neural Super-Resolution

Boosting face recognition via neural Super-Resolution Boosting face recognition via neural Super-Resolution Guillaume Berger, Cle ment Peyrard and Moez Baccouche Orange Labs - 4 rue du Clos Courtel, 35510 Cesson-Se vigne - France Abstract. We propose a two-step

More information

Partial Face Recognition

Partial Face Recognition Partial Face Recognition Shengcai Liao NLPR, CASIA April 29, 2015 Background Cooperated face recognition People are asked to stand in front of a camera with good illumination conditions Border pass, access

More information

Hierarchical Ensemble of Gabor Fisher Classifier for Face Recognition

Hierarchical Ensemble of Gabor Fisher Classifier for Face Recognition Hierarchical Ensemble of Gabor Fisher Classifier for Face Recognition Yu Su 1,2 Shiguang Shan,2 Xilin Chen 2 Wen Gao 1,2 1 School of Computer Science and Technology, Harbin Institute of Technology, Harbin,

More information

MULTI-POSE FACE HALLUCINATION VIA NEIGHBOR EMBEDDING FOR FACIAL COMPONENTS. Yanghao Li, Jiaying Liu, Wenhan Yang, Zongming Guo

MULTI-POSE FACE HALLUCINATION VIA NEIGHBOR EMBEDDING FOR FACIAL COMPONENTS. Yanghao Li, Jiaying Liu, Wenhan Yang, Zongming Guo MULTI-POSE FACE HALLUCINATION VIA NEIGHBOR EMBEDDING FOR FACIAL COMPONENTS Yanghao Li, Jiaying Liu, Wenhan Yang, Zongg Guo Institute of Computer Science and Technology, Peking University, Beijing, P.R.China,

More information

Experiments of Image Retrieval Using Weak Attributes

Experiments of Image Retrieval Using Weak Attributes Columbia University Computer Science Department Technical Report # CUCS 005-12 (2012) Experiments of Image Retrieval Using Weak Attributes Felix X. Yu, Rongrong Ji, Ming-Hen Tsai, Guangnan Ye, Shih-Fu

More information

Git Loss for Deep Face Recognition

Git Loss for Deep Face Recognition CALEFATI ET AL.: GIT LOSS FOR DEEP FACE RECOGNITION 1 Git Loss for Deep Face Recognition Alessandro Calefati *1 a.calefati@uninsubria.it Muhammad Kamran Janjua *2 mjanjua.bscs16seecs@seecs.edu.pk Shah

More information

Frankenstein: Learning Deep Face Representations using Small Data

Frankenstein: Learning Deep Face Representations using Small Data 1 Frankenstein: Learning Deep Face Representations using Small Data Guosheng Hu, Member, IEEE, Xiaojiang Peng, Yongxin Yang, Timothy M. Hospedales, and Jakob Verbeek arxiv:1603.06470v3 [cs.cv] 1 Sep 017

More information

MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction

MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction Ayush Tewari Michael Zollhofer Hyeongwoo Kim Pablo Garrido Florian Bernard Patrick Perez Christian Theobalt

More information

arxiv: v2 [cs.cv] 11 Apr 2016

arxiv: v2 [cs.cv] 11 Apr 2016 arxiv:1603.07057v2 [cs.cv] 11 Apr 2016 Do We Really Need to Collect Millions of Faces for Effective Face Recognition? Iacopo Masi 1, Anh Tuãn Trãn 1, Jatuporn Toy Leksut 1, Tal Hassner 2,3 and Gérard Medioni

More information

An efficient face recognition algorithm based on multi-kernel regularization learning

An efficient face recognition algorithm based on multi-kernel regularization learning Acta Technica 61, No. 4A/2016, 75 84 c 2017 Institute of Thermomechanics CAS, v.v.i. An efficient face recognition algorithm based on multi-kernel regularization learning Bi Rongrong 1 Abstract. A novel

More information

Intensity-Depth Face Alignment Using Cascade Shape Regression

Intensity-Depth Face Alignment Using Cascade Shape Regression Intensity-Depth Face Alignment Using Cascade Shape Regression Yang Cao 1 and Bao-Liang Lu 1,2 1 Center for Brain-like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai

More information

A FRAMEWORK OF EXTRACTING MULTI-SCALE FEATURES USING MULTIPLE CONVOLUTIONAL NEURAL NETWORKS. Kuan-Chuan Peng and Tsuhan Chen

A FRAMEWORK OF EXTRACTING MULTI-SCALE FEATURES USING MULTIPLE CONVOLUTIONAL NEURAL NETWORKS. Kuan-Chuan Peng and Tsuhan Chen A FRAMEWORK OF EXTRACTING MULTI-SCALE FEATURES USING MULTIPLE CONVOLUTIONAL NEURAL NETWORKS Kuan-Chuan Peng and Tsuhan Chen School of Electrical and Computer Engineering, Cornell University, Ithaca, NY

More information

Short Paper Boosting Sex Identification Performance

Short Paper Boosting Sex Identification Performance International Journal of Computer Vision 71(1), 111 119, 2007 c 2006 Springer Science + Business Media, LLC. Manufactured in the United States. DOI: 10.1007/s11263-006-8910-9 Short Paper Boosting Sex Identification

More information

arxiv: v3 [cs.cv] 24 Apr 2017

arxiv: v3 [cs.cv] 24 Apr 2017 A Light CNN for Deep Face Representation with Noisy Labels arxiv:1511.02683v3 [cs.cv] 24 Apr 2017 Xiang Wu, Ran He, Zhenan Sun, Tieniu Tan Center for Research on Intelligent Perception and Computing (CRIPAC),

More information

Virtual Training Samples and CRC based Test Sample Reconstruction and Face Recognition Experiments Wei HUANG and Li-ming MIAO

Virtual Training Samples and CRC based Test Sample Reconstruction and Face Recognition Experiments Wei HUANG and Li-ming MIAO 7 nd International Conference on Computational Modeling, Simulation and Applied Mathematics (CMSAM 7) ISBN: 978--6595-499-8 Virtual raining Samples and CRC based est Sample Reconstruction and Face Recognition

More information

Local Gradient Order Pattern for Face Representation and Recognition

Local Gradient Order Pattern for Face Representation and Recognition Local Gradient Order Pattern for Face Representation and Recognition Zhen Lei, Dong Yi, and Stan Z. Li Center for Biometrics and Security Research & National Laboratory of Pattern Recognition, Institute

More information

Pairwise Relational Networks for Face Recognition

Pairwise Relational Networks for Face Recognition Pairwise Relational Networks for Face Recognition Bong-Nam Kang 1[0000 0002 6818 7532], Yonghyun Kim 2[0000 0003 0038 7850], and Daijin Kim 1,2[0000 0002 8046 8521] 1 Department of Creative IT Engineering,

More information

Deep Learning Based Real-time Object Recognition System with Image Web Crawler

Deep Learning Based Real-time Object Recognition System with Image Web Crawler , pp.103-110 http://dx.doi.org/10.14257/astl.2016.142.19 Deep Learning Based Real-time Object Recognition System with Image Web Crawler Myung-jae Lee 1, Hyeok-june Jeong 1, Young-guk Ha 2 1 Department

More information

Toward More Realistic Face Recognition Evaluation Protocols for the YouTube Faces Database

Toward More Realistic Face Recognition Evaluation Protocols for the YouTube Faces Database Toward More Realistic Face Recognition Evaluation Protocols for the YouTube Faces Database Yoanna Martínez-Díaz, Heydi Méndez-Vázquez, Leyanis López-Avila Advanced Technologies Application Center (CENATAV)

More information

DeepIndex for Accurate and Efficient Image Retrieval

DeepIndex for Accurate and Efficient Image Retrieval DeepIndex for Accurate and Efficient Image Retrieval Yu Liu, Yanming Guo, Song Wu, Michael S. Lew Media Lab, Leiden Institute of Advance Computer Science Outline Motivation Proposed Approach Results Conclusions

More information

Generic Face Alignment Using an Improved Active Shape Model

Generic Face Alignment Using an Improved Active Shape Model Generic Face Alignment Using an Improved Active Shape Model Liting Wang, Xiaoqing Ding, Chi Fang Electronic Engineering Department, Tsinghua University, Beijing, China {wanglt, dxq, fangchi} @ocrserv.ee.tsinghua.edu.cn

More information

arxiv: v1 [cs.cv] 3 Mar 2018

arxiv: v1 [cs.cv] 3 Mar 2018 Unsupervised Learning of Face Representations Samyak Datta, Gaurav Sharma, C.V. Jawahar Georgia Institute of Technology, CVIT, IIIT Hyderabad, IIT Kanpur arxiv:1803.01260v1 [cs.cv] 3 Mar 2018 Abstract

More information

De-mark GAN: Removing Dense Watermark With Generative Adversarial Network

De-mark GAN: Removing Dense Watermark With Generative Adversarial Network De-mark GAN: Removing Dense Watermark With Generative Adversarial Network Jinlin Wu, Hailin Shi, Shu Zhang, Zhen Lei, Yang Yang, Stan Z. Li Center for Biometrics and Security Research & National Laboratory

More information

The HFB Face Database for Heterogeneous Face Biometrics Research

The HFB Face Database for Heterogeneous Face Biometrics Research The HFB Face Database for Heterogeneous Face Biometrics Research Stan Z. Li, Zhen Lei, Meng Ao Center for Biometrics and Security Research Institute of Automation, Chinese Academy of Sciences 95 Zhongguancun

More information

arxiv: v1 [cs.cv] 11 Apr 2018

arxiv: v1 [cs.cv] 11 Apr 2018 Unsupervised Segmentation of 3D Medical Images Based on Clustering and Deep Representation Learning Takayasu Moriya a, Holger R. Roth a, Shota Nakamura b, Hirohisa Oda c, Kai Nagara c, Masahiro Oda a,

More information

HENet: A Highly Efficient Convolutional Neural. Networks Optimized for Accuracy, Speed and Storage

HENet: A Highly Efficient Convolutional Neural. Networks Optimized for Accuracy, Speed and Storage HENet: A Highly Efficient Convolutional Neural Networks Optimized for Accuracy, Speed and Storage Qiuyu Zhu Shanghai University zhuqiuyu@staff.shu.edu.cn Ruixin Zhang Shanghai University chriszhang96@shu.edu.cn

More information

Face Recognition by Combining Kernel Associative Memory and Gabor Transforms

Face Recognition by Combining Kernel Associative Memory and Gabor Transforms Face Recognition by Combining Kernel Associative Memory and Gabor Transforms Author Zhang, Bai-ling, Leung, Clement, Gao, Yongsheng Published 2006 Conference Title ICPR2006: 18th International Conference

More information

arxiv: v1 [cs.cv] 2 Mar 2018

arxiv: v1 [cs.cv] 2 Mar 2018 Pose-Robust Face Recognition via Deep Residual Equivariant Mapping Kaidi Cao 2 Yu Rong 1,2 Cheng Li 2 Xiaoou Tang 1 Chen Change Loy 1 arxiv:1803.00839v1 [cs.cv] 2 Mar 2018 1 Department of Information Engineering,

More information

Bidirectional Recurrent Convolutional Networks for Video Super-Resolution

Bidirectional Recurrent Convolutional Networks for Video Super-Resolution Bidirectional Recurrent Convolutional Networks for Video Super-Resolution Qi Zhang & Yan Huang Center for Research on Intelligent Perception and Computing (CRIPAC) National Laboratory of Pattern Recognition

More information

Training Deep Face Recognition Systems with Synthetic Data

Training Deep Face Recognition Systems with Synthetic Data 1 Training Deep Face Recognition Systems with Synthetic Data Adam Kortylewski, Andreas Schneider, Thomas Gerig, Bernhard Egger, Andreas Morel-Forster, Thomas Vetter Department of Mathematics and Computer

More information

An End-to-End System for Unconstrained Face Verification with Deep Convolutional Neural Networks

An End-to-End System for Unconstrained Face Verification with Deep Convolutional Neural Networks An End-to-End System for Unconstrained Face Verification with Deep Convolutional Neural Networks Jun-Cheng Chen 1, Rajeev Ranjan 1, Amit Kumar 1, Ching-Hui Chen 1, Vishal M. Patel 2, and Rama Chellappa

More information

Content-Based Image Recovery

Content-Based Image Recovery Content-Based Image Recovery Hong-Yu Zhou and Jianxin Wu National Key Laboratory for Novel Software Technology Nanjing University, China zhouhy@lamda.nju.edu.cn wujx2001@nju.edu.cn Abstract. We propose

More information

Better than best: matching score based face registration

Better than best: matching score based face registration Better than best: based face registration Luuk Spreeuwers University of Twente Fac. EEMCS, Signals and Systems Group Hogekamp Building, 7522 NB Enschede The Netherlands l.j.spreeuwers@ewi.utwente.nl Bas

More information

DeepFace: Closing the Gap to Human-Level Performance in Face Verification

DeepFace: Closing the Gap to Human-Level Performance in Face Verification DeepFace: Closing the Gap to Human-Level Performance in Face Verification Yaniv Taigman Ming Yang Marc Aurelio Ranzato Facebook AI Group Menlo Park, CA, USA {yaniv, mingyang, ranzato}@fb.com Lior Wolf

More information

Eye Detection by Haar wavelets and cascaded Support Vector Machine

Eye Detection by Haar wavelets and cascaded Support Vector Machine Eye Detection by Haar wavelets and cascaded Support Vector Machine Vishal Agrawal B.Tech 4th Year Guide: Simant Dubey / Amitabha Mukherjee Dept of Computer Science and Engineering IIT Kanpur - 208 016

More information

Yunfeng Zhang 1, Huan Wang 2, Jie Zhu 1 1 Computer Science & Engineering Department, North China Institute of Aerospace

Yunfeng Zhang 1, Huan Wang 2, Jie Zhu 1 1 Computer Science & Engineering Department, North China Institute of Aerospace [Type text] [Type text] [Type text] ISSN : 0974-7435 Volume 10 Issue 20 BioTechnology 2014 An Indian Journal FULL PAPER BTAIJ, 10(20), 2014 [12526-12531] Exploration on the data mining system construction

More information

Human-Robot Interaction

Human-Robot Interaction Human-Robot Interaction Elective in Artificial Intelligence Lecture 6 Visual Perception Luca Iocchi DIAG, Sapienza University of Rome, Italy With contributions from D. D. Bloisi and A. Youssef Visual Perception

More information

Real-time Object Detection CS 229 Course Project

Real-time Object Detection CS 229 Course Project Real-time Object Detection CS 229 Course Project Zibo Gong 1, Tianchang He 1, and Ziyi Yang 1 1 Department of Electrical Engineering, Stanford University December 17, 2016 Abstract Objection detection

More information