Skin Lesion Attribute Detection for ISIC Using Mask-RCNN

Size: px
Start display at page:

Download "Skin Lesion Attribute Detection for ISIC Using Mask-RCNN"

Transcription

1 Skin Lesion Attribute Detection for ISIC 2018 Using Mask-RCNN Asmaa Aljuhani and Abhishek Kumar Department of Computer Science, Ohio State University, Columbus, USA Abstract We present an approach that utilizes Mask R-CNN method to detect different skin lesion attributes (Task2) of ISIC 2018 Challenge. In this approach, five pre-trained ResNet-101 networks are trained separately using augmented dataset of the original training data for skin lesion attributes. The model is evaluated using the training and validation datasets from the ISIC 2018 Challenge. Framework and Configuration Most image segmentation techniques are divided into 2 primary approaches. One takes advantage of convolution deconvolution models like unets while the other uses region proposals. We use the second approach utilizing Mask R-CNN 1 which was developed by building on Faster-RCNN 2 for image segmentation. Mask R-CNN is an improvement over Faster-RCNN. Faster-RCNN has 2 main stages. First is the RPN (Region Proposal Network) which proposes candidate bounding boxes for object detection/segmentation. The second stage works in two parts. It extracts features from the region proposals and feeds it to a classifier. The features for both the first stage(region proposal) and feature extraction are shared. Mask 1

2 R-CNN inherits these two stages. But in the second stage, Mask R-CNN also predicts an output mask for each of the RoI from region proposal. They utilize multitask loss on each of these RoI s. L = L cls + L bbox + L mask For feature extraction Mask R-CNN relies on a convolution neural network. Technically, this can be any CNN designed for object detection. We rely on the Mask RCNN implementation by Matterport. 3 We use ResNet50 and ResNet 101 as our backbone CNN with a learning momentum of 0.9 and decay rate of 0.1. We utilize various learning rates to get the best results. Data Pre-processing and Augmentation The training data for ISIC 2018 Challenge 4 (task 2) consists of 2594 training lesion images. For each training image, there is 5 binary mask corresponding to the five dermoscopic attributes. For validation purpose, we split the input images to the ratio of 90:10 training and testing sets. Image Tiling In order to overcome the shortage of the training data, every image was sliced into tiles of forth of its original size along the rows and columns and shifting by forth of the minimum between the width and the height of the tile size. Each tile was augmented with: 90, 180, 270 image rotations; and vertical and horizontal image flips. Mask tiles for the five attributes are generated following the same process. Mask tiles with no positive values were discarded, along with the corresponding image tile, for that specific attribute. The table 2 shows number of tiles for each attributes. 2

3 Table 1: Number of tiles for each attribute Globules Milia PigmentNet NegativeNet Streaks Training Testing Training Method Our skin lesion detection model utilized the Ohio Supercomputer Center 5 resources. The model consisted of five Mask RCNN networks that detect dermoscopic attributes separately. Each network is trained on the attribute s tiles dataset. The model is configured to detect two classes: background and lesion attribute. The training was performed for 100 epochs with a learning rate and learning momentum 0.9. The model is validated with the original training images. The Jaccard index score is computed between the predicted masks and the ground truth ones. To speed up the training process, Mask RCNN networks were initialized with COCO 6 weight prior to training. Validation and Results Since our model is trained on the augmented tiles dataset, we validated the model on the ISIC 2018 challenge training images. Table 2 shows the average of Jaccard index score on the different attributes. Table 2: The average of Jaccard index score Globules Milia PigmentNet NegativeNet Streaks Mean JS The model is also validated on 100 validation images with no ground truth masks using the ISIC 2018 challenge online submission system with a score of We also trained our model on full size images without any tiling or augmentation. This model performed significantly better. This model was also validated on 100 validation images 3

4 with no ground truth masks using the ISIC 2018 challenge online submission system with a score of Testing ISIC 2018 Challenge has 71 images for testing phase. We ran the model on the testing images and submitted the predicted masks to the submission portal. Lesion attribute detection sample results (a) (b) (c) (d) (e) Figure 1: Task2 lesion attribute detection with the highest Jaccard Index (top row shows predicted masks and the bttom row is the ground truth) (a)globules (b)milia like cyst (c)negative network (d)pigment network (e)streaks References (1) He, K.; Gkioxari, G.; Dollár, P.; Girshick, R. B. CoRR 2017, abs/ (2) Ren, S.; He, K.; Girshick, R. B.; Sun, J. CoRR 2015, abs/ (3) Abdulla, W. Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

5 (a) (b) (c) (d) (e) Figure 2: Task2 lesion attribute detection with Jaccard Index < 0.2 (top row shows predicted masks and the bottom row is the ground truth) (a)globules (b)milia like cyst (c)negative network (d)pigment network (e)streaks (4) Tschandl, P.; Rosendahl, C.; Kittler, H. ArXiv e-prints 2018, (5) Center, O. S. Ohio Supercomputer Center (6) Lin, T.-Y.; Maire, M.; Belongie, S.; Bourdev, L.; Girshick, R.; Hays, J.; Perona, P.; Ramanan, D.; Zitnick, C. L.; Dollár, P. ArXiv e-prints 2014, 5

CIS680: Vision & Learning Assignment 2.b: RPN, Faster R-CNN and Mask R-CNN Due: Nov. 21, 2018 at 11:59 pm

CIS680: Vision & Learning Assignment 2.b: RPN, Faster R-CNN and Mask R-CNN Due: Nov. 21, 2018 at 11:59 pm CIS680: Vision & Learning Assignment 2.b: RPN, Faster R-CNN and Mask R-CNN Due: Nov. 21, 2018 at 11:59 pm Instructions This is an individual assignment. Individual means each student must hand in their

More information

Skin Lesion Classification and Segmentation for Imbalanced Classes using Deep Learning

Skin Lesion Classification and Segmentation for Imbalanced Classes using Deep Learning Skin Lesion Classification and Segmentation for Imbalanced Classes using Deep Learning Mohammed K. Amro, Baljit Singh, and Avez Rizvi mamro@sidra.org, bsingh@sidra.org, arizvi@sidra.org Abstract - This

More information

Mask R-CNN. presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma

Mask R-CNN. presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma Mask R-CNN presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma Mask R-CNN Background Related Work Architecture Experiment Mask R-CNN Background Related Work Architecture Experiment Background From left

More information

arxiv: v1 [cs.cv] 15 Oct 2018

arxiv: v1 [cs.cv] 15 Oct 2018 Instance Segmentation and Object Detection with Bounding Shape Masks Ha Young Kim 1,2,*, Ba Rom Kang 2 1 Department of Financial Engineering, Ajou University Worldcupro 206, Yeongtong-gu, Suwon, 16499,

More information

Mask R-CNN. By Kaiming He, Georgia Gkioxari, Piotr Dollar and Ross Girshick Presented By Aditya Sanghi

Mask R-CNN. By Kaiming He, Georgia Gkioxari, Piotr Dollar and Ross Girshick Presented By Aditya Sanghi Mask R-CNN By Kaiming He, Georgia Gkioxari, Piotr Dollar and Ross Girshick Presented By Aditya Sanghi Types of Computer Vision Tasks http://cs231n.stanford.edu/ Semantic vs Instance Segmentation Image

More information

arxiv: v2 [cs.cv] 30 Sep 2018

arxiv: v2 [cs.cv] 30 Sep 2018 A Detection and Segmentation Architecture for Skin Lesion Segmentation on Dermoscopy Images arxiv:1809.03917v2 [cs.cv] 30 Sep 2018 Chengyao Qian, Ting Liu, Hao Jiang, Zhe Wang, Pengfei Wang, Mingxin Guan

More information

Classifying a specific image region using convolutional nets with an ROI mask as input

Classifying a specific image region using convolutional nets with an ROI mask as input Classifying a specific image region using convolutional nets with an ROI mask as input 1 Sagi Eppel Abstract Convolutional neural nets (CNN) are the leading computer vision method for classifying images.

More information

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun Presented by Tushar Bansal Objective 1. Get bounding box for all objects

More information

REGION AVERAGE POOLING FOR CONTEXT-AWARE OBJECT DETECTION

REGION AVERAGE POOLING FOR CONTEXT-AWARE OBJECT DETECTION REGION AVERAGE POOLING FOR CONTEXT-AWARE OBJECT DETECTION Kingsley Kuan 1, Gaurav Manek 1, Jie Lin 1, Yuan Fang 1, Vijay Chandrasekhar 1,2 Institute for Infocomm Research, A*STAR, Singapore 1 Nanyang Technological

More information

Mask R-CNN. Kaiming He, Georgia, Gkioxari, Piotr Dollar, Ross Girshick Presenters: Xiaokang Wang, Mengyao Shi Feb. 13, 2018

Mask R-CNN. Kaiming He, Georgia, Gkioxari, Piotr Dollar, Ross Girshick Presenters: Xiaokang Wang, Mengyao Shi Feb. 13, 2018 Mask R-CNN Kaiming He, Georgia, Gkioxari, Piotr Dollar, Ross Girshick Presenters: Xiaokang Wang, Mengyao Shi Feb. 13, 2018 1 Common computer vision tasks Image Classification: one label is generated for

More information

Finding Tiny Faces Supplementary Materials

Finding Tiny Faces Supplementary Materials Finding Tiny Faces Supplementary Materials Peiyun Hu, Deva Ramanan Robotics Institute Carnegie Mellon University {peiyunh,deva}@cs.cmu.edu 1. Error analysis Quantitative analysis We plot the distribution

More information

Lecture 5: Object Detection

Lecture 5: Object Detection Object Detection CSED703R: Deep Learning for Visual Recognition (2017F) Lecture 5: Object Detection Bohyung Han Computer Vision Lab. bhhan@postech.ac.kr 2 Traditional Object Detection Algorithms Region-based

More information

Final Report: Smart Trash Net: Waste Localization and Classification

Final Report: Smart Trash Net: Waste Localization and Classification Final Report: Smart Trash Net: Waste Localization and Classification Oluwasanya Awe oawe@stanford.edu Robel Mengistu robel@stanford.edu December 15, 2017 Vikram Sreedhar vsreed@stanford.edu Abstract Given

More information

Geometry-aware Traffic Flow Analysis by Detection and Tracking

Geometry-aware Traffic Flow Analysis by Detection and Tracking Geometry-aware Traffic Flow Analysis by Detection and Tracking 1,2 Honghui Shi, 1 Zhonghao Wang, 1,2 Yang Zhang, 1,3 Xinchao Wang, 1 Thomas Huang 1 IFP Group, Beckman Institute at UIUC, 2 IBM Research,

More information

arxiv: v3 [cs.cv] 2 Jun 2017

arxiv: v3 [cs.cv] 2 Jun 2017 Incorporating the Knowledge of Dermatologists to Convolutional Neural Networks for the Diagnosis of Skin Lesions arxiv:1703.01976v3 [cs.cv] 2 Jun 2017 Iván González-Díaz Department of Signal Theory and

More information

Evaluating Mask R-CNN Performance for Indoor Scene Understanding

Evaluating Mask R-CNN Performance for Indoor Scene Understanding Evaluating Mask R-CNN Performance for Indoor Scene Understanding Badruswamy, Shiva shivalgo@stanford.edu June 12, 2018 1 Motivation and Problem Statement Indoor robotics and Augmented Reality are fast

More information

YOLO9000: Better, Faster, Stronger

YOLO9000: Better, Faster, Stronger YOLO9000: Better, Faster, Stronger Date: January 24, 2018 Prepared by Haris Khan (University of Toronto) Haris Khan CSC2548: Machine Learning in Computer Vision 1 Overview 1. Motivation for one-shot object

More information

Object detection with CNNs

Object detection with CNNs Object detection with CNNs 80% PASCAL VOC mean0average0precision0(map) 70% 60% 50% 40% 30% 20% 10% Before CNNs After CNNs 0% 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 year Region proposals

More information

An Analysis of Scale Invariance in Object Detection SNIP

An Analysis of Scale Invariance in Object Detection SNIP An Analysis of Scale Invariance in Object Detection SNIP Bharat Singh Larry S. Davis University of Maryland, College Park {bharat,lsd}@cs.umd.edu Abstract An analysis of different techniques for recognizing

More information

arxiv: v2 [cs.cv] 18 Jul 2017

arxiv: v2 [cs.cv] 18 Jul 2017 PHAM, ITO, KOZAKAYA: BISEG 1 arxiv:1706.02135v2 [cs.cv] 18 Jul 2017 BiSeg: Simultaneous Instance Segmentation and Semantic Segmentation with Fully Convolutional Networks Viet-Quoc Pham quocviet.pham@toshiba.co.jp

More information

Object Detection on Self-Driving Cars in China. Lingyun Li

Object Detection on Self-Driving Cars in China. Lingyun Li Object Detection on Self-Driving Cars in China Lingyun Li Introduction Motivation: Perception is the key of self-driving cars Data set: 10000 images with annotation 2000 images without annotation (not

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

Hand Detection For Grab-and-Go Groceries

Hand Detection For Grab-and-Go Groceries Hand Detection For Grab-and-Go Groceries Xianlei Qiu Stanford University xianlei@stanford.edu Shuying Zhang Stanford University shuyingz@stanford.edu Abstract Hands detection system is a very critical

More information

Supplementary Material: Pixelwise Instance Segmentation with a Dynamically Instantiated Network

Supplementary Material: Pixelwise Instance Segmentation with a Dynamically Instantiated Network Supplementary Material: Pixelwise Instance Segmentation with a Dynamically Instantiated Network Anurag Arnab and Philip H.S. Torr University of Oxford {anurag.arnab, philip.torr}@eng.ox.ac.uk 1. Introduction

More information

R-FCN: Object Detection with Really - Friggin Convolutional Networks

R-FCN: Object Detection with Really - Friggin Convolutional Networks R-FCN: Object Detection with Really - Friggin Convolutional Networks Jifeng Dai Microsoft Research Li Yi Tsinghua Univ. Kaiming He FAIR Jian Sun Microsoft Research NIPS, 2016 Or Region-based Fully Convolutional

More information

3 Object Detection. BVM 2018 Tutorial: Advanced Deep Learning Methods. Paul F. Jaeger, Division of Medical Image Computing

3 Object Detection. BVM 2018 Tutorial: Advanced Deep Learning Methods. Paul F. Jaeger, Division of Medical Image Computing 3 Object Detection BVM 2018 Tutorial: Advanced Deep Learning Methods Paul F. Jaeger, of Medical Image Computing What is object detection? classification segmentation obj. detection (1 label per pixel)

More information

MULTI-SCALE OBJECT DETECTION WITH FEATURE FUSION AND REGION OBJECTNESS NETWORK. Wenjie Guan, YueXian Zou*, Xiaoqun Zhou

MULTI-SCALE OBJECT DETECTION WITH FEATURE FUSION AND REGION OBJECTNESS NETWORK. Wenjie Guan, YueXian Zou*, Xiaoqun Zhou MULTI-SCALE OBJECT DETECTION WITH FEATURE FUSION AND REGION OBJECTNESS NETWORK Wenjie Guan, YueXian Zou*, Xiaoqun Zhou ADSPLAB/Intelligent Lab, School of ECE, Peking University, Shenzhen,518055, China

More information

arxiv: v1 [cs.cv] 19 Mar 2018

arxiv: v1 [cs.cv] 19 Mar 2018 arxiv:1803.07066v1 [cs.cv] 19 Mar 2018 Learning Region Features for Object Detection Jiayuan Gu 1, Han Hu 2, Liwei Wang 1, Yichen Wei 2 and Jifeng Dai 2 1 Key Laboratory of Machine Perception, School of

More information

Object Detection Based on Deep Learning

Object Detection Based on Deep Learning Object Detection Based on Deep Learning Yurii Pashchenko AI Ukraine 2016, Kharkiv, 2016 Image classification (mostly what you ve seen) http://tutorial.caffe.berkeleyvision.org/caffe-cvpr15-detection.pdf

More information

arxiv: v1 [cs.cv] 26 Jul 2018

arxiv: v1 [cs.cv] 26 Jul 2018 A Better Baseline for AVA Rohit Girdhar João Carreira Carl Doersch Andrew Zisserman DeepMind Carnegie Mellon University University of Oxford arxiv:1807.10066v1 [cs.cv] 26 Jul 2018 Abstract We introduce

More information

An Analysis of Scale Invariance in Object Detection SNIP

An Analysis of Scale Invariance in Object Detection SNIP An Analysis of Scale Invariance in Object Detection SNIP Bharat Singh Larry S. Davis University of Maryland, College Park {bharat,lsd}@cs.umd.edu Abstract An analysis of different techniques for recognizing

More information

[Supplementary Material] Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors

[Supplementary Material] Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors [Supplementary Material] Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors Junhyug Noh Soochan Lee Beomsu Kim Gunhee Kim Department of Computer Science and Engineering

More information

SSD: Single Shot MultiBox Detector. Author: Wei Liu et al. Presenter: Siyu Jiang

SSD: Single Shot MultiBox Detector. Author: Wei Liu et al. Presenter: Siyu Jiang SSD: Single Shot MultiBox Detector Author: Wei Liu et al. Presenter: Siyu Jiang Outline 1. Motivations 2. Contributions 3. Methodology 4. Experiments 5. Conclusions 6. Extensions Motivation Motivation

More information

arxiv: v1 [cs.cv] 16 Nov 2018

arxiv: v1 [cs.cv] 16 Nov 2018 Improving Rotated Text Detection with Rotation Region Proposal Networks Jing Huang 1, Viswanath Sivakumar 1, Mher Mnatsakanyan 1,2 and Guan Pang 1 1 Facebook Inc. 2 University of California, Berkeley November

More information

Counting Vehicles with Cameras

Counting Vehicles with Cameras Counting Vehicles with Cameras Luca Ciampi 1, Giuseppe Amato 1, Fabrizio Falchi 1, Claudio Gennaro 1, and Fausto Rabitti 1 Institute of Information, Science and Technologies of the National Research Council

More information

Spatial Localization and Detection. Lecture 8-1

Spatial Localization and Detection. Lecture 8-1 Lecture 8: Spatial Localization and Detection Lecture 8-1 Administrative - Project Proposals were due on Saturday Homework 2 due Friday 2/5 Homework 1 grades out this week Midterm will be in-class on Wednesday

More information

Joint Object Detection and Viewpoint Estimation using CNN features

Joint Object Detection and Viewpoint Estimation using CNN features Joint Object Detection and Viewpoint Estimation using CNN features Carlos Guindel, David Martín and José M. Armingol cguindel@ing.uc3m.es Intelligent Systems Laboratory Universidad Carlos III de Madrid

More information

arxiv: v1 [cs.cv] 19 Feb 2019

arxiv: v1 [cs.cv] 19 Feb 2019 Detector-in-Detector: Multi-Level Analysis for Human-Parts Xiaojie Li 1[0000 0001 6449 2727], Lu Yang 2[0000 0003 3857 3982], Qing Song 2[0000000346162200], and Fuqiang Zhou 1[0000 0001 9341 9342] arxiv:1902.07017v1

More information

A Semi-Automatic 2D solution for Vehicle Speed Estimation from Monocular Videos

A Semi-Automatic 2D solution for Vehicle Speed Estimation from Monocular Videos A Semi-Automatic 2D solution for Vehicle Speed Estimation from Monocular Videos Amit Kumar, Pirazh Khorramshahi, Wei-An Lin, Prithviraj Dhar, Jun-Cheng Chen and Rama Chellappa Center for Automation Research,

More information

arxiv: v2 [cs.cv] 8 Apr 2018

arxiv: v2 [cs.cv] 8 Apr 2018 Single-Shot Object Detection with Enriched Semantics Zhishuai Zhang 1 Siyuan Qiao 1 Cihang Xie 1 Wei Shen 1,2 Bo Wang 3 Alan L. Yuille 1 Johns Hopkins University 1 Shanghai University 2 Hikvision Research

More information

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Shaoqing Ren Kaiming He Ross Girshick Jian Sun Present by: Yixin Yang Mingdong Wang 1 Object Detection 2 1 Applications Basic

More information

Todo before next class

Todo before next class Todo before next class Each project group should submit a short project report (4 pages presentation slides) including 1. Problem definition 2. Related work 3. Preliminary results 4. Future plan Submission:

More information

arxiv: v1 [cs.cv] 9 Aug 2017

arxiv: v1 [cs.cv] 9 Aug 2017 BlitzNet: A Real-Time Deep Network for Scene Understanding Nikita Dvornik Konstantin Shmelkov Julien Mairal Cordelia Schmid Inria arxiv:1708.02813v1 [cs.cv] 9 Aug 2017 Abstract Real-time scene understanding

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

arxiv: v2 [cs.cv] 10 Oct 2018

arxiv: v2 [cs.cv] 10 Oct 2018 Net: An Accurate and Efficient Single-Shot Object Detector for Autonomous Driving Qijie Zhao 1, Tao Sheng 1, Yongtao Wang 1, Feng Ni 1, Ling Cai 2 1 Institute of Computer Science and Technology, Peking

More information

R-FCN++: Towards Accurate Region-Based Fully Convolutional Networks for Object Detection

R-FCN++: Towards Accurate Region-Based Fully Convolutional Networks for Object Detection The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) R-FCN++: Towards Accurate Region-Based Fully Convolutional Networks for Object Detection Zeming Li, 1 Yilun Chen, 2 Gang Yu, 2 Yangdong

More information

Yiqi Yan. May 10, 2017

Yiqi Yan. May 10, 2017 Yiqi Yan May 10, 2017 P a r t I F u n d a m e n t a l B a c k g r o u n d s Convolution Single Filter Multiple Filters 3 Convolution: case study, 2 filters 4 Convolution: receptive field receptive field

More information

Introduction to Deep Learning for Facial Understanding Part III: Regional CNNs

Introduction to Deep Learning for Facial Understanding Part III: Regional CNNs Introduction to Deep Learning for Facial Understanding Part III: Regional CNNs Raymond Ptucha, Rochester Institute of Technology, USA Tutorial-9 May 19, 218 www.nvidia.com/dli R. Ptucha 18 1 Fair Use Agreement

More information

Unsupervised domain adaptation of deep object detectors

Unsupervised domain adaptation of deep object detectors Unsupervised domain adaptation of deep object detectors Debjeet Majumdar 1 and Vinay P. Namboodiri2 Indian Institute of Technology, Kanpur - Computer Science and Engineering Kalyanpur, Kanpur, Uttar Pradesh

More information

A MultiPath Network for Object Detection

A MultiPath Network for Object Detection ZAGORUYKO et al.: A MULTIPATH NETWORK FOR OBJECT DETECTION 1 A MultiPath Network for Object Detection Sergey Zagoruyko, Adam Lerer, Tsung-Yi Lin, Pedro O. Pinheiro, Sam Gross, Soumith Chintala, Piotr Dollár

More information

Deep learning for object detection. Slides from Svetlana Lazebnik and many others

Deep learning for object detection. Slides from Svetlana Lazebnik and many others Deep learning for object detection Slides from Svetlana Lazebnik and many others Recent developments in object detection 80% PASCAL VOC mean0average0precision0(map) 70% 60% 50% 40% 30% 20% 10% Before deep

More information

Efficient Segmentation-Aided Text Detection For Intelligent Robots

Efficient Segmentation-Aided Text Detection For Intelligent Robots Efficient Segmentation-Aided Text Detection For Intelligent Robots Junting Zhang, Yuewei Na, Siyang Li, C.-C. Jay Kuo University of Southern California Outline Problem Definition and Motivation Related

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

Show, Discriminate, and Tell: A Discriminatory Image Captioning Model with Deep Neural Networks

Show, Discriminate, and Tell: A Discriminatory Image Captioning Model with Deep Neural Networks Show, Discriminate, and Tell: A Discriminatory Image Captioning Model with Deep Neural Networks Zelun Luo Department of Computer Science Stanford University zelunluo@stanford.edu Te-Lin Wu Department of

More information

Robust Detection for Red Blood Cells in Thin Blood Smear Microscopy Using Deep Learning

Robust Detection for Red Blood Cells in Thin Blood Smear Microscopy Using Deep Learning Robust Detection for Red Blood Cells in Thin Blood Smear Microscopy Using Deep Learning By Yasmin Kassim PhD Candidate in University of Missouri-Columbia Supervised by Dr. Kannappan Palaniappan Mentored

More information

Image Captioning with Attention

Image Captioning with Attention ing with Attention Blaine Rister (blaine@stanford.edu), Dieterich Lawson (jdlawson@stanford.edu) 1. Introduction In the past few years, neural networks have fueled dramatic advances in image classication.

More information

Object Detection. CS698N Final Project Presentation AKSHAT AGARWAL SIDDHARTH TANWAR

Object Detection. CS698N Final Project Presentation AKSHAT AGARWAL SIDDHARTH TANWAR Object Detection CS698N Final Project Presentation AKSHAT AGARWAL SIDDHARTH TANWAR Problem Description Arguably the most important part of perception Long term goals for object recognition: Generalization

More information

arxiv: v1 [cs.cv] 5 Dec 2017

arxiv: v1 [cs.cv] 5 Dec 2017 R-FCN-3000 at 30fps: Decoupling Detection and Classification Bharat Singh*1 Hengduo Li*2 Abhishek Sharma3 Larry S. Davis1 University of Maryland, College Park 1 Fudan University2 Gobasco AI Labs3 arxiv:1712.01802v1

More information

arxiv: v3 [cs.cv] 12 Mar 2018

arxiv: v3 [cs.cv] 12 Mar 2018 Improving Object Localization with Fitness NMS and Bounded IoU Loss Lachlan Tychsen-Smith, Lars Petersson CSIRO (Data6) CSIRO-Synergy Building, Acton, ACT, 26 Lachlan.Tychsen-Smith@data6.csiro.au, Lars.Petersson@data6.csiro.au

More information

Encoder-Decoder Networks for Semantic Segmentation. Sachin Mehta

Encoder-Decoder Networks for Semantic Segmentation. Sachin Mehta Encoder-Decoder Networks for Semantic Segmentation Sachin Mehta Outline > Overview of Semantic Segmentation > Encoder-Decoder Networks > Results What is Semantic Segmentation? Input: RGB Image Output:

More information

Object Detection in Sports Videos

Object Detection in Sports Videos Object Detection in Sports Videos M. Burić, M. Pobar, M. Ivašić-Kos University of Rijeka/Department of Informatics, Rijeka, Croatia matija.buric@hep.hr, marinai@inf.uniri.hr, mpobar@inf.uniri.hr Abstract

More information

Learning to Segment Object Candidates

Learning to Segment Object Candidates Learning to Segment Object Candidates Pedro Pinheiro, Ronan Collobert and Piotr Dollar Presented by - Sivaraman, Kalpathy Sitaraman, M.S. in Computer Science, University of Virginia Facebook Artificial

More information

Boundary-aware Instance Segmentation

Boundary-aware Instance Segmentation Boundary-aware Instance Segmentation Zeeshan Hayder,2, Xuming He 2, Australian National University & 2 Data6/CSIRO Mathieu Salzmann 3 3 CVLab, EPFL, Switzerland Abstract We address the problem of instance-level

More information

Robust Hand Detection and Classification in Vehicles and in the Wild

Robust Hand Detection and Classification in Vehicles and in the Wild Robust Hand Detection and Classification in Vehicles and in the Wild T. Hoang Ngan Le Kha Gia Quach Chenchen Zhu Chi Nhan Duong Khoa Luu Marios Savvides CyLab Biometrics Center, Carnegie Mellon University

More information

IN order to distinguish melanoma from benign lesions, dermatologists. Fully Convolutional Neural Networks to Detect Clinical Dermoscopic Features

IN order to distinguish melanoma from benign lesions, dermatologists. Fully Convolutional Neural Networks to Detect Clinical Dermoscopic Features TO APPEAR IN: JBHI - SPECIAL ISSUE ON SKIN LESION IMAGE ANALYSIS FOR MELANOMA DETECTION c 208 IEEE Fully Convolutional Neural Networks to Detect Clinical Dermoscopic Features Jeremy Kawahara and Ghassan

More information

Deep Learning for Object detection & localization

Deep Learning for Object detection & localization Deep Learning for Object detection & localization RCNN, Fast RCNN, Faster RCNN, YOLO, GAP, CAM, MSROI Aaditya Prakash Sep 25, 2018 Image classification Image classification Whole of image is classified

More information

DeepIM: Deep Iterative Matching for 6D Pose Estimation - Supplementary Material

DeepIM: Deep Iterative Matching for 6D Pose Estimation - Supplementary Material DeepIM: Deep Iterative Matching for 6D Pose Estimation - Supplementary Material Yi Li 1, Gu Wang 1, Xiangyang Ji 1, Yu Xiang 2, and Dieter Fox 2 1 Tsinghua University, BNRist 2 University of Washington

More information

MCMOT: Multi-Class Multi-Object Tracking using Changing Point Detection

MCMOT: Multi-Class Multi-Object Tracking using Changing Point Detection MCMOT: Multi-Class Multi-Object Tracking using Changing Point Detection ILSVRC 2016 Object Detection from Video Byungjae Lee¹, Songguo Jin¹, Enkhbayar Erdenee¹, Mi Young Nam², Young Gui Jung², Phill Kyu

More information

arxiv: v2 [cs.cv] 28 May 2017

arxiv: v2 [cs.cv] 28 May 2017 Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection Xianzhi Du 1, Mostafa El-Khamy 2, Jungwon Lee 2, Larry S. Davis 1 arxiv:1610.03466v2 [cs.cv] 28 May 2017 1 Computer

More information

arxiv: v3 [cs.cv] 18 Oct 2017

arxiv: v3 [cs.cv] 18 Oct 2017 SSH: Single Stage Headless Face Detector Mahyar Najibi* Pouya Samangouei* Rama Chellappa University of Maryland arxiv:78.3979v3 [cs.cv] 8 Oct 27 najibi@cs.umd.edu Larry S. Davis {pouya,rama,lsd}@umiacs.umd.edu

More information

arxiv: v1 [cs.cv] 29 Nov 2018

arxiv: v1 [cs.cv] 29 Nov 2018 Grid R-CNN Xin Lu 1 Buyu Li 1 Yuxin Yue 1 Quanquan Li 1 Junjie Yan 1 1 SenseTime Group Limited {luxin,libuyu,yueyuxin,liquanquan,yanjunjie}@sensetime.com arxiv:1811.12030v1 [cs.cv] 29 Nov 2018 Abstract

More information

Convolutional Neural Networks: Applications and a short timeline. 7th Deep Learning Meetup Kornel Kis Vienna,

Convolutional Neural Networks: Applications and a short timeline. 7th Deep Learning Meetup Kornel Kis Vienna, Convolutional Neural Networks: Applications and a short timeline 7th Deep Learning Meetup Kornel Kis Vienna, 1.12.2016. Introduction Currently a master student Master thesis at BME SmartLab Started deep

More information

Deep Residual Architecture for Skin Lesion Segmentation

Deep Residual Architecture for Skin Lesion Segmentation Deep Residual Architecture for Skin Lesion Segmentation Venkatesh G M 1, Naresh Y G 1, Suzanne Little 2, and Noel O Connor 2 1 Insight Centre for Data Analystics-DCU, Dublin, Ireland 2 Dublin City University,

More information

Pedestrian Detection based on Deep Fusion Network using Feature Correlation

Pedestrian Detection based on Deep Fusion Network using Feature Correlation Pedestrian Detection based on Deep Fusion Network using Feature Correlation Yongwoo Lee, Toan Duc Bui and Jitae Shin School of Electronic and Electrical Engineering, Sungkyunkwan University, Suwon, South

More information

arxiv: v2 [cs.cv] 3 Sep 2018

arxiv: v2 [cs.cv] 3 Sep 2018 Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning Max Ferguson 1 Ronay Ak 2 Yung-Tsun Tina Lee 2 and Kincho. H. Law 1 arxiv:1808.02518v2 [cs.cv]

More information

Yield Estimation using faster R-CNN

Yield Estimation using faster R-CNN Yield Estimation using faster R-CNN 1 Vidhya Sagar, 2 Sailesh J.Jain and 2 Arjun P. 1 Assistant Professor, 2 UG Scholar, Department of Computer Engineering and Science SRM Institute of Science and Technology,Chennai,

More information

Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning

Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning Max Ferguson 1 Ronay Ak 2 Yung-Tsun Tina Lee 2 and Kincho. H. Law 1 Abstract Automatic detection

More information

R-FCN Object Detection Ensemble based on Object Resolution and Image Quality Rasmussen, Christoffer Bøgelund; Nasrollahi, Kamal; Moeslund, Thomas B.

R-FCN Object Detection Ensemble based on Object Resolution and Image Quality Rasmussen, Christoffer Bøgelund; Nasrollahi, Kamal; Moeslund, Thomas B. Aalborg Universitet R-FCN Object Detection Ensemble based on Object Resolution and Image Quality Rasmussen, Christoffer Bøgelund; Nasrollahi, Kamal; Moeslund, Thomas B. Published in: International Joint

More information

arxiv: v1 [cs.cv] 30 Jul 2018

arxiv: v1 [cs.cv] 30 Jul 2018 Acquisition of Localization Confidence for Accurate Object Detection Borui Jiang 1,3, Ruixuan Luo 1,3, Jiayuan Mao 2,4, Tete Xiao 1,3, and Yuning Jiang 4 arxiv:1807.11590v1 [cs.cv] 30 Jul 2018 1 School

More information

Learning Globally Optimized Object Detector via Policy Gradient

Learning Globally Optimized Object Detector via Policy Gradient Learning Globally Optimized Object Detector via Policy Gradient Yongming Rao 1,2,3, Dahua Lin 4, Jiwen Lu 1,2,3, Jie Zhou 1,2,3 1 Department of Automation, Tsinghua University 2 State Key Lab of Intelligent

More information

arxiv: v1 [cs.cv] 23 Jan 2019

arxiv: v1 [cs.cv] 23 Jan 2019 DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images Yuying Ge 1, Ruimao Zhang 1, Lingyun Wu 2, Xiaogang Wang 1, Xiaoou Tang 1, and

More information

arxiv: v2 [cs.cv] 23 Nov 2017

arxiv: v2 [cs.cv] 23 Nov 2017 Light-Head R-CNN: In Defense of Two-Stage Object Detector Zeming Li 1, Chao Peng 2, Gang Yu 2, Xiangyu Zhang 2, Yangdong Deng 1, Jian Sun 2 1 School of Software, Tsinghua University, {lizm15@mails.tsinghua.edu.cn,

More information

arxiv: v1 [cs.cv] 8 Jul 2018

arxiv: v1 [cs.cv] 8 Jul 2018 arxiv:1807.02842v1 [cs.cv] 8 Jul 2018 Auto-Context R-CNN Bo Li, Tianfu Wu, Lun Zhang and Rufeng Chu YunOS BU, Alibaba Group Department of Electrical and Computer Engineering and the Visual Narrative Cluster,

More information

Semantic Soft Segmentation Supplementary Material

Semantic Soft Segmentation Supplementary Material Semantic Soft Segmentation Supplementary Material YAĞIZ AKSOY, MIT CSAIL and ETH Zürich TAE-HYUN OH, MIT CSAIL SYLVAIN PARIS, Adobe Research MARC POLLEFEYS, ETH Zürich and Microsoft WOJCIECH MATUSIK, MIT

More information

SNIPER: Efficient Multi-Scale Training

SNIPER: Efficient Multi-Scale Training SNIPER: Efficient Multi-Scale Training Bharat Singh Mahyar Najibi Larry S. Davis University of Maryland, College Park {bharat,najibi,lsd}@cs.umd.edu Abstract We present SNIPER, an algorithm for performing

More information

R-FCN-3000 at 30fps: Decoupling Detection and Classification

R-FCN-3000 at 30fps: Decoupling Detection and Classification R-FCN-3000 at 30fps: Decoupling Detection and Classification Bharat Singh* 1 Hengduo Li* 2 Abhishek Sharma 3 Larry S. Davis 1 University of Maryland, College Park 1 Fudan University 2 Gobasco AI Labs 3

More information

Lecture 7: Semantic Segmentation

Lecture 7: Semantic Segmentation Semantic Segmentation CSED703R: Deep Learning for Visual Recognition (207F) Segmenting images based on its semantic notion Lecture 7: Semantic Segmentation Bohyung Han Computer Vision Lab. bhhanpostech.ac.kr

More information

Traffic Multiple Target Detection on YOLOv2

Traffic Multiple Target Detection on YOLOv2 Traffic Multiple Target Detection on YOLOv2 Junhong Li, Huibin Ge, Ziyang Zhang, Weiqin Wang, Yi Yang Taiyuan University of Technology, Shanxi, 030600, China wangweiqin1609@link.tyut.edu.cn Abstract Background

More information

arxiv: v1 [cs.cv] 26 May 2017

arxiv: v1 [cs.cv] 26 May 2017 arxiv:1705.09587v1 [cs.cv] 26 May 2017 J. JEONG, H. PARK AND N. KWAK: UNDER REVIEW IN BMVC 2017 1 Enhancement of SSD by concatenating feature maps for object detection Jisoo Jeong soo3553@snu.ac.kr Hyojin

More information

arxiv: v1 [cs.cv] 10 Jan 2019

arxiv: v1 [cs.cv] 10 Jan 2019 Region Proposal by Guided Anchoring Jiaqi Wang 1 Kai Chen 1 Shuo Yang 2 Chen Change Loy 3 Dahua Lin 1 1 CUHK - SenseTime Joint Lab, The Chinese University of Hong Kong 2 Amazon Rekognition 3 Nanyang Technological

More information

Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection

Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection 2017 IEEE Winter Conference on Applications of Computer Vision Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection Xianzhi Du 1, Mostafa El-Khamy 2, Jungwon Lee 3,

More information

Context Refinement for Object Detection

Context Refinement for Object Detection Context Refinement for Object Detection Zhe Chen, Shaoli Huang, and Dacheng Tao UBTECH Sydney AI Centre, SIT, FEIT, University of Sydney, Australia {zche4307}@uni.sydney.edu.au {shaoli.huang, dacheng.tao}@sydney.edu.au

More information

Contextual Attention for Hand Detection in the Wild

Contextual Attention for Hand Detection in the Wild Contextual Attention for Hand Detection in the Wild Supreeth Narasimhaswamy 1, Zhengwei Wei 1, Yang Wang 1, Justin Zhang 2, Minh Hoai 1 1 Stony Brook University, 2 Caltech, Joint First Authors Abstract

More information

Computer Vision Lecture 16

Computer Vision Lecture 16 Computer Vision Lecture 16 Deep Learning Applications 11.01.2017 Bastian Leibe RWTH Aachen http://www.vision.rwth-aachen.de leibe@vision.rwth-aachen.de Announcements Seminar registration period starts

More information

arxiv: v1 [cs.cv] 15 Aug 2018

arxiv: v1 [cs.cv] 15 Aug 2018 SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection arxiv:88.97v [cs.cv] 5 Aug 8 Yonghyun Kim [ 8 785], Bong-Nam Kang [ 688 75], and Daijin Kim [ 86 85] Department

More information

Using RGB, Depth, and Thermal Data for Improved Hand Detection

Using RGB, Depth, and Thermal Data for Improved Hand Detection Using RGB, Depth, and Thermal Data for Improved Hand Detection Rachel Luo, Gregory Luppescu Department of Electrical Engineering Stanford University {rsluo, gluppes}@stanford.edu Abstract Hand detection

More information

Person Part Segmentation based on Weak Supervision

Person Part Segmentation based on Weak Supervision JIANG, CHI: PERSON PART SEGMENTATION BASED ON WEAK SUPERVISION 1 Person Part Segmentation based on Weak Supervision Yalong Jiang 1 yalong.jiang@connect.polyu.hk Zheru Chi 1 chi.zheru@polyu.edu.hk 1 Department

More information

Optimizing Object Detection:

Optimizing Object Detection: Lecture 10: Optimizing Object Detection: A Case Study of R-CNN, Fast R-CNN, and Faster R-CNN Visual Computing Systems Today s task: object detection Image classification: what is the object in this image?

More information

A Multi-task Framework for Skin Lesion Detection and Segmentation

A Multi-task Framework for Skin Lesion Detection and Segmentation A Multi-task Framework for Skin Lesion Detection and Segmentation Sulaiman Vesal 1 ( ), Shreyas Malakarjun Patil 1,2 ( ), Nishant Ravikumar 1, and Andreas K. Maier 1 1 Pattern Recognition Lab, Friedrich-Alexander-Universität

More information

arxiv: v1 [cs.ro] 24 Jul 2018

arxiv: v1 [cs.ro] 24 Jul 2018 ClusterNet: Instance Segmentation in RGB-D Images Lin Shao, Ye Tian, Jeannette Bohg Stanford University United States lins2,yetian1,bohg@stanford.edu arxiv:1807.08894v1 [cs.ro] 24 Jul 2018 Abstract: We

More information