POINT CLOUD DEEP LEARNING
|
|
- Maurice Lynch
- 5 years ago
- Views:
Transcription
1 POINT CLOUD DEEP LEARNING Innfarn Yoo, 3/29/28 / 57
2 Introduction AGENDA Previous Work Method Result Conclusion 2 / 57
3 INTRODUCTION 3 / 57
4 2D OBJECT CLASSIFICATION Deep Learning for 2D Object Classification Convolutional Neural Network (CNN) for 2D images works really well AlexNet, ResNet, & GoogLeNet R-CNN Fast R-CNN Faster R-CNN Mask R-CNN Recent 2D image classification can even extract precise boundaries of objects (FCN Mask R-CNN) [] He et al., Mask R-CNN (27) 4 / 57
5 3D OBJECT CLASSIFICATION Deep Learning for 3D Object Classification 3D object classification approaches are getting more attentions Collecting 3D point data is easier and cheaper than before (LiDAR & other sensors) Size of data is bigger than 2D images Open datasets are increasing Recent researches approaches human level detection accuracy MVCNN, ShapeNet, PointNet, VoxNet, VoxelNet, & VRN Ensemble [2] Zhou and Tuzel, VoxelNet (27) 5 / 57
6 GOALS The goals of our method Evaluating & comparing different types of Neural Network models for 3D object classification Providing the generic framework to test multiple 3D neural network models Simple & easy to implement neural network models Fast preprocessing (remove bottleneck of loading, sampling, & jittering 3D data) 6 / 57
7 PREVIOUS WORK 7 / 57
8 3D POINT-BASED APPROACHES 3D Points Neural Nets PointNet First 3D point-based classification Unordered dataset Transform Multi-Layer Perceptron (MLP) Max Pool (MP) Classification [5] Qi et al., PointNet (27) 8 / 57
9 PIXEL-BASED APPROACHES 3D 2D Projections Neural Nets Multi-Layer Perceptron (MLP) Convolutional Neural Network (CNN) [4] Krizhevsky et al., AlexNet (22) Multi-View Convolutional Neural Network (MVCNN) [3] Su et al., MVCNN (25) 9 / 57
10 VOXEL-BASED APPROACHES 3D Points Voxels Neural Nets VoxNet [7] Broke et al., VRN Ensemble (26) VRN Ensemble VoxelNet [6] Maturana and Scherer, VoxNet (25) [2] Zhou and Tuzel, VoxelNet (27) / 57
11 METHOD / 57
12 PREPROCESSING Requirement Loading 3D polygonal objects Required Operations on 3D objects Sampling, Shuffling, Jittering, Scaling, & Rotating Projection, & Voxelization Python interface is not that good for multi-core processing (or multi-threading) # of objects is notoriously for single-core processing 2 / 57
13 nn3d_trainer (C++) Trainer: C++ program Load 3D Objects Sample Points Thread 3D Point Sample FRAMEWORK Basic Pipeline Thread 2 3D Point Sample Loading 3D Object Sampler Threads Thread 3 3D Point Sample Epoch #i Thread N 3D Point Sample Converter Pixel, Point, Voxel Converter Pixel, Point, Voxel Converter Pixel, Point, Voxel Converter Pixel, Point, Voxel Increase epoch Call Python NN Model Functions: Train, Test, Eval, Report, & Save 3 / 57
14 3D DATASETS MODELNET MODELNET4 SHAPENET CORE V2 Princeton ModelNet Data Categories 4,93 Objects (2 GB) OFF (CAD) File Format Princeton ModelNet Data 4 Categories 2,43 Objects ( GB) OFF (CAD) File Format ShapeNet 55 Categories 5,9 Objects (9 GB) OBJ File Format 4 / 57
15 Point-Based Models NEURAL NETWORK MODELS Pixel-Based Models Voxel-Based Models 5 / 57
16 POINT-BASED NEURAL NETWORK MODELS Types of Models Preprocessing: Rotate randomly Scale randomly Uniform sampling on 3D object surfaces Sample 248 points Shuffle points Tested Models Multi-Layer Perceptron (MLP) Multi Rotational MLPs Single Orientation CNN Multi Rotational CNNs Multi Rotational Resample & Max Pool Layers ResNet-like 6 / 57
17 7 / 57
18 POINT-BASED NEURAL NETWORK MODELS MLP 3D points ReLU + Dropout Softmax Cross Entropy Flatten Vector Fully Connected Layer Class Onehot Vector 8 / 57
19 POINT-BASED NEURAL NETWORK MODELS Multi Rotational MLPs 3D points ReLU + Dropout Softmax Cross Entropy Random 3x3 Rotation 3D Conv Layer Max Pooling Layer Flatten Vector Fully Connected Layer Class Onehot Vector 9 / 57
20 POINT-BASED NEURAL NETWORK MODELS Single Orientation CNN 3D points ReLU + Dropout ReLU + Dropout Softmax Cross Entropy Random 3x3 Rotation 3D Conv Layer Max Pooling Layer Flatten Vector Fully Connected Layer Class Onehot Vector 2 / 57
21 POINT-BASED NEURAL NETWORK MODELS Multi Rotational CNNs ReLU + Dropout ReLU + Dropout Softmax Cross Entropy 3D points Random 3x3 Rotation 3D Conv Layer Max Pooling Layer Flatten Vector Fully Connected Layer Class Onehot Vector 2 / 57
22 POINT-BASED NEURAL NETWORK MODELS Multi Rotational Resample & Max Pool Layers ReLU + Dropout ReLU + Dropout Softmax Cross Entropy 3D points Random 3x3 Rotation Resample Layer Max Pooling Layer Flatten Vector Fully Connected Layer Class Onehot Vector 22 / 57
23 POINT-BASED NEURAL NETWORK MODELS ResNet-like 3D points ReLU + Dropout ReLU + Dropout ReLU + Dropout Softmax Cross Entropy Random 3x3 Rotation Resample Layer Max Pooling Layer Flatten Vector Fully Connected Layer Class Onehot Vector 23 / 57
24 PIXEL-BASED NEURAL NETWORK MODELS Types of Models Preprocessing: Sample 892 points Tested Models: MLP Same as point-based models Depth-only orthogonal projection Depth-Only Orthogonal MVCNN 32x32 or 64x64 Generating multiple rotations 64x64x5 & 64x64x 24 / 57
25 25 / 57
26 PIXEL-BASED NEURAL NETWORK MODELS MLP Images (32x32x5) Softmax Cross Entropy Flatten Vector Fully Connected Layer Class Onehot Vector 26 / 57
27 PIXEL-BASED NEURAL NETWORK MODELS Depth-Only Orthogonal MVCNN Images (32x32x5) Softmax Cross Entropy Concat Image Separation 3D Conv Layer Max Pooling Layer Flatten Vector Fully Connected Layer Class Onehot Vector 27 / 57
28 VOXEL-BASED NEURAL NETWORK MODELS Types of Models Preprocessing: Sample 892 points Same as point based models Voxelization Tested Models: MLP CNN ResNet-like 3D points Voxels Each voxel has intensity. ~. how many points hit same voxel 32x32x32 & 64x64x64 28 / 57
29 29 / 57
30 VOXEL-BASED NEURAL NETWORK MODELS MLP Images (32x32x5) Softmax Cross Entropy Flatten Vector Fully Connected Layer Class Onehot Vector 3 / 57
31 VOXEL-BASED NEURAL NETWORK MODELS CNN Voxels 32x32x32 Softmax Cross Entropy 3D Conv Layer Max Pooling Layer Flatten Vector Fully Connected Layer Class Onehot Vector 3 / 57
32 VOXEL-BASED NEURAL NETWORK MODELS ResNet-like Voxels 32x32x32 Softmax Cross Entropy Concat 3D Conv Layer Avg Pooling Layer Resample Layer Max Pooling Layer Flatten Vector Fully Connected Layer Class Onehot Vector 32 / 57
33 IMPLEMENTATION System Setup System: Ubuntu 6.4, RAM 32 GB & 64 GB, & SSD 52 GB NVIDIA Quadro P6, Quadro M6, & GeForce Titan X GCC 5.2. for C++ x Python 3.5 TensorFlow-GPU v.5. NumPy. 33 / 57
34 HYPER PARAMETERS Object Perturbation Random Rotations: -25 ~ 25 degree Random Scaling:.7 ~. Learning Rate:. Keep Probability (Dropout layer):.7 Max Epochs: Batch Size: 32 Number of Random Rotations: 2 Voxel Dim: 32x32x32 MVCNN Number of Views: 5 34 / 57
35 RESULT 35 / 57
36 MODELNET # OF TEST & TRAIN OBJECTS # of Test Models # of Train Models / 57 table toilet monitor bathtub sofa chair desk dresser night_stand bed
37 MODELNET ACCURACY % Iter: Train Accu Test Accu map / 57 PC MLP PC CNN PC MLPs PC CNNs PC MP PC ResNet PX MLP PX MVCNN VX MLP VX CNN VX ResNet
38 MODELNET4 # OF TEST & TRAIN OBJECTS # of Test Models # of Train Models / 57
39 MODELNET4 ACCURACY % Iter: Train Accu Test Accu map / 57 PC MLP PC CNN PC MLPs PC CNNs PC MP PC ResNet PX MLP PX MVCNN VX MLP VX CNN VX ResNet
40 MODELNET4 ACCURACY 7 CATEGORIES (# OF TRAIN OBJECTS > 4) # of Test Models # of Train Models / 57
41 MODELNET4, 7 CATEGORIES ACCURACY % Iter: Train Accu Test Accu map / 57 PC MLP PC CNN PC MLPs PC CNNs PC MP PC ResNet PX MLP PX MVCNN VX MLP VX CNN VX ResNet
42 MODELNET4 ACCURACY CATEGORIES (# OF TRAIN OBJECTS > 3) # of Test Models # of Train Models / 57
43 MODELNET4, CATEGORIES ACCURACY Train Accu Test Accu map / 57 PC MLP PC CNN PC MLPs PC CNNs PC MP PC ResNet PX MLP PX MVCNN VX MLP VX CNN VX ResNet
44 MODELNET4 ACCURACY 7 CATEGORIES (# OF TRAIN OBJECTS > 2) # of Test Models # of Train Models / 57
45 MODELNET4,7 CATEGORIES ACCURACY % Iter: Train Accu Test Accu map / 57 PC MLP PC CNN PC MLPs PC CNNs PC MP PC ResNet PX MLP PX MVCNN VX MLP VX CNN VX ResNet
46 hours 3. MODELNET PERFORMANCE seconds PC MLP PC CNN PC MLPs PC CNNs PC MP PC ResNet PX MLP PX MVCNN VX MLP VX CNN VX ResNet PC MLP PC CNN PC MLPs PC CNNs PC MP PC ResNet PX MLP PX MVCNN VX MLP VX CNN VX ResNet Total Training Time Inference Time Per Batch 46 / 57
47 hours 8. MODELNET4 PERFORMANCE seconds PC MLP PC CNN PC MLPs PC CNNs PC MP PC ResNet PX MLP PX MVCNN VX MLP VX CNN VX ResNet PC MLP PC CNN PC MLPs PC CNNs PC MP PC ResNet PX MLP PX MVCNN VX MLP VX CNN VX ResNet Total Training Time Inference Time Per Batch 47 / 57
48 SHAPENET CORE V2 ACCURACY ShapeNet has pretty big dataset % Train Accu Test Accu map Iter: 6 9 GB of dataset 9 Only tested 3 NN models 8 Point MP 7 6 Depth-Only MVCNN 5 4 Voxel CNN 3 2 PC MP PX MVCNN VX CNN 48 / 57
49 TRAIN ACCURACY GRAPH PC MLP PC MLPs PC CNN PC CNNs PC MP PC ResNet PX MLP PX MVCNN VX MLP VX CNN VX ResNet / 57
50 TEST ACCURACY GRAPH PC MLP PC MLPs PC CNN PC CNNs PC MP PC ResNet PX MLP PX MVCNN VX MLP VX CNN VX ResNet / 57
51 2.5 CROSS ENTROPY CONVERGENCE GRAPH PC MLP 2.5 PC MLPs 2.5 PC CNN 2.5 PC CNNs PC MP 2.5 PC ResNet 2.5 PX MLP 2.5 PX MVCNN VX MLP 2.5 VX CNN 2.5 VX ResNet / 57
52 CONCLUSION 52 / 57
53 CONCLUSION Models Voxel ResNet and Voxel CNN provide best result on 3D object classification Unordered vs. Ordered: Unordered data (point cloud) could be learned, but lower accuracy and higher computation cost than ordered data Projection vs. Voxelization: Voxelization provides better result with similar computation cost (converge faster, & more precise) Strict comparisons with previous methods are not done yet Sampling and jittering methods are different (cannot directly compare yet) 53 / 57
54 CONCLUSION Dataset Evaluation ModelNet & ModelNet4 Some categories have too small training and testing objects Lowering classification accuracy ModelNet4, 7 categories (# of training objects > 4) Achieved 98% accuracy Partial dataset from ModelNet4 (Categories that have more than 4 3D objects) # of train 3D objects in a category matters ShapeNetCore.v2 # of 3D objects are big enough, but many object but many duplicated objects 54 / 57
55 FUTURE WORK Running entire procedures in CUDA Using NVIDIA GVDB Will have advantages of Sparse Voxels Strict comparisons with previous methods PointNet, VRN Ensemble, etc Extending methods to captured dataset (e.g. KITTI) Train set is too small Need to investigate whether Generative Adversarial Networks (GAN) can alleviate this problem or not 55 / 57
56 REFERENCE [] He et al., 27, Mask R-CNN [2] Zhou and Tuzel, 27, VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection [3] Su et al., 25, Multi-view convolutional neural networks for 3d shape recognition [4] Krizhevsky et al., 22, ImageNet Classification with Deep Convolutional Neural Networks [5] Qi et al., 27, Pointnet: Deep learning on point sets for 3d classification and segmentation [6] Maturana and Scherer, 25, VoxNet: A 3D Convolutional Neural Network for Real-Time Object Recognition [7] Broke et al., 26, Generative and Discriminative Voxel Modeling with Convolutional Neural Networks [8] He et al., 26, Deep residual learning for image recognition [9] Goodfellow et al., 24, Generative adversarial nets [] Girshick, 25, Fast R-CNN [] Ren et al., 25, Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks [2] Chang et al., 25, ShapeNet: An Information-Rich 3D Model Repository [3] Wu et al., 25, 3D ShapeNets: A Deep Representation for Volumetric Shapes [4] Wu et al., 24, 3D ShapeNets for 2.5D Object Recognition and Next-Best-View Prediction 56 / 57
57 57 / 57
MULTI-LEVEL 3D CONVOLUTIONAL NEURAL NETWORK FOR OBJECT RECOGNITION SAMBIT GHADAI XIAN LEE ADITYA BALU SOUMIK SARKAR ADARSH KRISHNAMURTHY
MULTI-LEVEL 3D CONVOLUTIONAL NEURAL NETWORK FOR OBJECT RECOGNITION SAMBIT GHADAI XIAN LEE ADITYA BALU SOUMIK SARKAR ADARSH KRISHNAMURTHY Outline Object Recognition Multi-Level Volumetric Representations
More informationVolumetric and Multi-View CNNs for Object Classification on 3D Data Supplementary Material
Volumetric and Multi-View CNNs for Object Classification on 3D Data Supplementary Material Charles R. Qi Hao Su Matthias Nießner Angela Dai Mengyuan Yan Leonidas J. Guibas Stanford University 1. Details
More informationPointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. Charles R. Qi* Hao Su* Kaichun Mo Leonidas J. Guibas
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation Charles R. Qi* Hao Su* Kaichun Mo Leonidas J. Guibas Big Data + Deep Representation Learning Robot Perception Augmented Reality
More informationDeep Learning with Tensorflow AlexNet
Machine Learning and Computer Vision Group Deep Learning with Tensorflow http://cvml.ist.ac.at/courses/dlwt_w17/ AlexNet Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton, "Imagenet classification
More informationPointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space Sikai Zhong February 14, 2018 COMPUTER SCIENCE Table of contents 1. PointNet 2. PointNet++ 3. Experiments 1 PointNet Property
More informationECCV Presented by: Boris Ivanovic and Yolanda Wang CS 331B - November 16, 2016
ECCV 2016 Presented by: Boris Ivanovic and Yolanda Wang CS 331B - November 16, 2016 Fundamental Question What is a good vector representation of an object? Something that can be easily predicted from 2D
More information3D Object Classification via Spherical Projections
3D Object Classification via Spherical Projections Zhangjie Cao 1,QixingHuang 2,andRamaniKarthik 3 1 School of Software Tsinghua University, China 2 Department of Computer Science University of Texas at
More informationConvolutional 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 information3D Object Detection with Sparse Sampling Neural Networks. Ryan Goy
3D Object Detection with Sparse Sampling Neural Networks by Ryan Goy A thesis submitted in partial satisfaction of the requirements for the degree of Master of Science, Plan II in Electrical Engineering
More informationKeras: Handwritten Digit Recognition using MNIST Dataset
Keras: Handwritten Digit Recognition using MNIST Dataset IIT PATNA January 31, 2018 1 / 30 OUTLINE 1 Keras: Introduction 2 Installing Keras 3 Keras: Building, Testing, Improving A Simple Network 2 / 30
More informationSupplementary A. Overview. C. Time and Space Complexity. B. Shape Retrieval. D. Permutation Invariant SOM. B.1. Dataset
Supplementary A. Overview This supplementary document provides more technical details and experimental results to the main paper. Shape retrieval experiments are demonstrated with ShapeNet Core55 dataset
More informationDeep Learning for Computer Vision II
IIIT Hyderabad Deep Learning for Computer Vision II C. V. Jawahar Paradigm Shift Feature Extraction (SIFT, HoG, ) Part Models / Encoding Classifier Sparrow Feature Learning Classifier Sparrow L 1 L 2 L
More information3D model classification using convolutional neural network
3D model classification using convolutional neural network JunYoung Gwak Stanford jgwak@cs.stanford.edu Abstract Our goal is to classify 3D models directly using convolutional neural network. Most of existing
More informationKeras: Handwritten Digit Recognition using MNIST Dataset
Keras: Handwritten Digit Recognition using MNIST Dataset IIT PATNA February 9, 2017 1 / 24 OUTLINE 1 Introduction Keras: Deep Learning library for Theano and TensorFlow 2 Installing Keras Installation
More informationInception and Residual Networks. Hantao Zhang. Deep Learning with Python.
Inception and Residual Networks Hantao Zhang Deep Learning with Python https://en.wikipedia.org/wiki/residual_neural_network Deep Neural Network Progress from Large Scale Visual Recognition Challenge (ILSVRC)
More informationGenerative Modeling with Convolutional Neural Networks. Denis Dus Data Scientist at InData Labs
Generative Modeling with Convolutional Neural Networks Denis Dus Data Scientist at InData Labs What we will discuss 1. 2. 3. 4. Discriminative vs Generative modeling Convolutional Neural Networks How to
More informationMask 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 informationLearning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks
Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks Kripasindhu Sarkar 1,2, Basavaraj Hampiholi 2, Kiran Varanasi 1, and Didier Stricker 1,2 1 DFKI Kaiserslautern 2 Technische
More informationInference Optimization Using TensorRT with Use Cases. Jack Han / 한재근 Solutions Architect NVIDIA
Inference Optimization Using TensorRT with Use Cases Jack Han / 한재근 Solutions Architect NVIDIA Search Image NLP Maps TensorRT 4 Adoption Use Cases Speech Video AI Inference is exploding 1 Billion Videos
More informationDeep Residual Learning
Deep Residual Learning MSRA @ ILSVRC & COCO 2015 competitions Kaiming He with Xiangyu Zhang, Shaoqing Ren, Jifeng Dai, & Jian Sun Microsoft Research Asia (MSRA) MSRA @ ILSVRC & COCO 2015 Competitions 1st
More informationarxiv: v1 [cs.cv] 2 Dec 2018
PVRNet: Point-View Relation Neural Network for 3D Shape Recognition Haoxuan You 1, Yifan Feng 2, Xibin Zhao 1, hangqing Zou 3, Rongrong Ji 2, Yue Gao 1 1 BNRist, KLISS, School of Software, Tsinghua University,
More informationDeep Learning Explained Module 4: Convolution Neural Networks (CNN or Conv Nets)
Deep Learning Explained Module 4: Convolution Neural Networks (CNN or Conv Nets) Sayan D. Pathak, Ph.D., Principal ML Scientist, Microsoft Roland Fernandez, Senior Researcher, Microsoft Module Outline
More informationConvolutional Neural Networks. Computer Vision Jia-Bin Huang, Virginia Tech
Convolutional Neural Networks Computer Vision Jia-Bin Huang, Virginia Tech Today s class Overview Convolutional Neural Network (CNN) Training CNN Understanding and Visualizing CNN Image Categorization:
More informationFuzzy Set Theory in Computer Vision: Example 3
Fuzzy Set Theory in Computer Vision: Example 3 Derek T. Anderson and James M. Keller FUZZ-IEEE, July 2017 Overview Purpose of these slides are to make you aware of a few of the different CNN architectures
More information3D Deep Learning on Geometric Forms. Hao Su
3D Deep Learning on Geometric Forms Hao Su Many 3D representations are available Candidates: multi-view images depth map volumetric polygonal mesh point cloud primitive-based CAD models 3D representation
More informationCS468: 3D Deep Learning on Point Cloud Data. class label part label. Hao Su. image. May 10, 2017
CS468: 3D Deep Learning on Point Cloud Data class label part label Hao Su image. May 10, 2017 Agenda Point cloud generation Point cloud analysis CVPR 17, Point Set Generation Pipeline render CVPR 17, Point
More informationDeep Learning for 3D Shape Classification Based on Volumetric Density and Surface Approximation Clues
Deep Learning for 3D Shape Classification Based on Volumetric Density and Surface Approximation Clues Ludovico Minto, Pietro Zanuttigh and Giampaolo Pagnutti Department of Information Engineering, University
More informationDEEP NEURAL NETWORKS CHANGING THE AUTONOMOUS VEHICLE LANDSCAPE. Dennis Lui August 2017
DEEP NEURAL NETWORKS CHANGING THE AUTONOMOUS VEHICLE LANDSCAPE Dennis Lui August 2017 THE RISE OF GPU COMPUTING APPLICATIONS 10 7 10 6 GPU-Computing perf 1.5X per year 1000X by 2025 ALGORITHMS 10 5 1.1X
More informationObject 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 informationStructured Prediction using Convolutional Neural Networks
Overview Structured Prediction using Convolutional Neural Networks Bohyung Han bhhan@postech.ac.kr Computer Vision Lab. Convolutional Neural Networks (CNNs) Structured predictions for low level computer
More informationCENG 783. Special topics in. Deep Learning. AlchemyAPI. Week 11. Sinan Kalkan
CENG 783 Special topics in Deep Learning AlchemyAPI Week 11 Sinan Kalkan TRAINING A CNN Fig: http://www.robots.ox.ac.uk/~vgg/practicals/cnn/ Feed-forward pass Note that this is written in terms of the
More informationAdvanced Video Analysis & Imaging
Advanced Video Analysis & Imaging (5LSH0), Module 09B Machine Learning with Convolutional Neural Networks (CNNs) - Workout Farhad G. Zanjani, Clint Sebastian, Egor Bondarev, Peter H.N. de With ( p.h.n.de.with@tue.nl
More information3D Deep Learning
3D Deep Learning Tutorial@CVPR2017 Hao Su (UCSD) Leonidas Guibas (Stanford) Michael Bronstein (Università della Svizzera Italiana) Evangelos Kalogerakis (UMass) Jimei Yang (Adobe Research) Charles Qi (Stanford)
More informationPerceptron: This is convolution!
Perceptron: This is convolution! v v v Shared weights v Filter = local perceptron. Also called kernel. By pooling responses at different locations, we gain robustness to the exact spatial location of image
More informationNVIDIA FOR DEEP LEARNING. Bill Veenhuis
NVIDIA FOR DEEP LEARNING Bill Veenhuis bveenhuis@nvidia.com Nvidia is the world s leading ai platform ONE ARCHITECTURE CUDA 2 GPU: Perfect Companion for Accelerating Apps & A.I. CPU GPU 3 Intro to AI AGENDA
More informationarxiv: v1 [cs.cv] 28 Nov 2018
MeshNet: Mesh Neural Network for 3D Shape Representation Yutong Feng, 1 Yifan Feng, 2 Haoxuan You, 1 Xibin Zhao 1, Yue Gao 1 1 BNRist, KLISS, School of Software, Tsinghua University, China. 2 School of
More informationDeep Learning for Computer Vision with MATLAB By Jon Cherrie
Deep Learning for Computer Vision with MATLAB By Jon Cherrie 2015 The MathWorks, Inc. 1 Deep learning is getting a lot of attention "Dahl and his colleagues won $22,000 with a deeplearning system. 'We
More informationSparse 3D Convolutional Neural Networks for Large-Scale Shape Retrieval
Sparse 3D Convolutional Neural Networks for Large-Scale Shape Retrieval Alexandr Notchenko, Ermek Kapushev, Evgeny Burnaev {avnotchenko,kapushev,burnaevevgeny}@gmail.com Skolkovo Institute of Science and
More informationDefense Data Generation in Distributed Deep Learning System Se-Yoon Oh / ADD-IDAR
Defense Data Generation in Distributed Deep Learning System Se-Yoon Oh / 2017. 10. 31 syoh@add.re.kr Page 1/36 Overview 1. Introduction 2. Data Generation Synthesis 3. Distributed Deep Learning 4. Conclusions
More informationCOMP9444 Neural Networks and Deep Learning 7. Image Processing. COMP9444 c Alan Blair, 2017
COMP9444 Neural Networks and Deep Learning 7. Image Processing COMP9444 17s2 Image Processing 1 Outline Image Datasets and Tasks Convolution in Detail AlexNet Weight Initialization Batch Normalization
More informationInception Network Overview. David White CS793
Inception Network Overview David White CS793 So, Leonardo DiCaprio dreams about dreaming... https://m.media-amazon.com/images/m/mv5bmjaxmzy3njcxnf5bml5banbnxkftztcwnti5otm0mw@@._v1_sy1000_cr0,0,675,1 000_AL_.jpg
More informationConvolutional Neural Networks
NPFL114, Lecture 4 Convolutional Neural Networks Milan Straka March 25, 2019 Charles University in Prague Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics unless otherwise
More informationDeep Learning for Computer Vision
Deep Learning for Computer Vision Lecture 7: Universal Approximation Theorem, More Hidden Units, Multi-Class Classifiers, Softmax, and Regularization Peter Belhumeur Computer Science Columbia University
More informationBeam Search for Learning a Deep Convolutional Neural Network of 3D Shapes
Beam Search for Learning a Deep Convolutional Neural Network of 3D Shapes Xu Xu and Sinisa Todorovic School of Electrical Engineering and Computer Science Oregon State University, Corvallis, Oregon 97330
More informationCNNS FROM THE BASICS TO RECENT ADVANCES. Dmytro Mishkin Center for Machine Perception Czech Technical University in Prague
CNNS FROM THE BASICS TO RECENT ADVANCES Dmytro Mishkin Center for Machine Perception Czech Technical University in Prague ducha.aiki@gmail.com OUTLINE Short review of the CNN design Architecture progress
More informationClassification of 3D Shapes with Convolutional Neural Networks
Classification of D Shapes with Convolutional Neural Networks Leonid Keselman Stanford University leonidk@stanford.edu various designs and tests of convolutional neural networks to solve this object classification
More informationDeconvolutions in Convolutional Neural Networks
Overview Deconvolutions in Convolutional Neural Networks Bohyung Han bhhan@postech.ac.kr Computer Vision Lab. Convolutional Neural Networks (CNNs) Deconvolutions in CNNs Applications Network visualization
More informationMulti-Task Self-Supervised Visual Learning
Multi-Task Self-Supervised Visual Learning Sikai Zhong March 4, 2018 COMPUTER SCIENCE Table of contents 1. Introduction 2. Self-supervised Tasks 3. Architectures 4. Experiments 1 Introduction Self-supervised
More informationIntro to Deep Learning. Slides Credit: Andrej Karapathy, Derek Hoiem, Marc Aurelio, Yann LeCunn
Intro to Deep Learning Slides Credit: Andrej Karapathy, Derek Hoiem, Marc Aurelio, Yann LeCunn Why this class? Deep Features Have been able to harness the big data in the most efficient and effective
More information3D Object Classification using Shape Distributions and Deep Learning
3D Object Classification using Shape Distributions and Deep Learning Melvin Low Stanford University mwlow@cs.stanford.edu Abstract This paper shows that the Absolute Angle shape distribution (AAD) feature
More informationFuzzy Set Theory in Computer Vision: Example 3, Part II
Fuzzy Set Theory in Computer Vision: Example 3, Part II Derek T. Anderson and James M. Keller FUZZ-IEEE, July 2017 Overview Resource; CS231n: Convolutional Neural Networks for Visual Recognition https://github.com/tuanavu/stanford-
More informationEFFICIENT INFERENCE WITH TENSORRT. Han Vanholder
EFFICIENT INFERENCE WITH TENSORRT Han Vanholder AI INFERENCING IS EXPLODING 2 Trillion Messages Per Day On LinkedIn 500M Daily active users of iflytek 140 Billion Words Per Day Translated by Google 60
More informationLearning to generate 3D shapes
Learning to generate 3D shapes Subhransu Maji College of Information and Computer Sciences University of Massachusetts, Amherst http://people.cs.umass.edu/smaji August 10, 2018 @ Caltech Creating 3D shapes
More informationSpatial 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 information3D Convolutional Neural Networks for Landing Zone Detection from LiDAR
3D Convolutional Neural Networks for Landing Zone Detection from LiDAR Daniel Mataruna and Sebastian Scherer Presented by: Sabin Kafle Outline Introduction Preliminaries Approach Volumetric Density Mapping
More informationCross-domain Deep Encoding for 3D Voxels and 2D Images
Cross-domain Deep Encoding for 3D Voxels and 2D Images Jingwei Ji Stanford University jingweij@stanford.edu Danyang Wang Stanford University danyangw@stanford.edu 1. Introduction 3D reconstruction is one
More informationContent-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 informationLearning Descriptor Networks for 3D Shape Synthesis and Analysis
Learning Descriptor Networks for 3D Shape Synthesis and Analysis Jianwen Xie 1, Zilong Zheng 2, Ruiqi Gao 2, Wenguan Wang 2,3, Song-Chun Zhu 2, Ying Nian Wu 2 1 Hikvision Research Institute 2 University
More informationUsing Faster-RCNN to Improve Shape Detection in LIDAR
Using Faster-RCNN to Improve Shape Detection in LIDAR TJ Melanson Stanford University Stanford, CA 94305 melanson@stanford.edu Abstract In this paper, I propose a method for extracting objects from unordered
More information3D CONVOLUTIONAL NEURAL NETWORKS BY MODAL FUSION
3D CONVOLUTIONAL NEURAL NETWORKS BY MODAL FUSION Yusuke Yoshiyasu, Eiichi Yoshida AIST Soeren Pirk, Leonidas Guibas Stanford University ABSTRACT We propose multi-view and volumetric convolutional neural
More informationImplementing Deep Learning for Video Analytics on Tegra X1.
Implementing Deep Learning for Video Analytics on Tegra X1 research@hertasecurity.com Index Who we are, what we do Video analytics pipeline Video decoding Facial detection and preprocessing DNN: learning
More informationarxiv: v4 [cs.cv] 27 Nov 2016
FusionNet: 3D Object Classification Using Multiple Data Representations Vishakh Hegde Stanford and Matroid vishakh@matroid.com Reza Zadeh Stanford and Matroid reza@matroid.com arxiv:1607.05695v4 [cs.cv]
More informationCNN Basics. Chongruo Wu
CNN Basics Chongruo Wu Overview 1. 2. 3. Forward: compute the output of each layer Back propagation: compute gradient Updating: update the parameters with computed gradient Agenda 1. Forward Conv, Fully
More informationDeepIM: 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 informationFace 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 informationA NEW COMPUTING ERA JENSEN HUANG, FOUNDER & CEO GTC CHINA 2017
A NEW COMPUTING ERA JENSEN HUANG, FOUNDER & CEO GTC CHINA 2017 TWO FORCES DRIVING THE FUTURE OF COMPUTING 10 7 Transistors (thousands) 10 6 10 5 1.1X per year 10 4 10 3 10 2 1.5X per year Single-threaded
More informationLearning Adversarial 3D Model Generation with 2D Image Enhancer
The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) Learning Adversarial 3D Model Generation with 2D Image Enhancer Jing Zhu, Jin Xie, Yi Fang NYU Multimedia and Visual Computing Lab
More informationStudy of Residual Networks for Image Recognition
Study of Residual Networks for Image Recognition Mohammad Sadegh Ebrahimi Stanford University sadegh@stanford.edu Hossein Karkeh Abadi Stanford University hosseink@stanford.edu Abstract Deep neural networks
More informationMoonRiver: Deep Neural Network in C++
MoonRiver: Deep Neural Network in C++ Chung-Yi Weng Computer Science & Engineering University of Washington chungyi@cs.washington.edu Abstract Artificial intelligence resurges with its dramatic improvement
More informationDEEP LEARNING FOR 3D SHAPE CLASSIFICATION FROM MULTIPLE DEPTH MAPS. Pietro Zanuttigh and Ludovico Minto
DEEP LEARNING FOR 3D SHAPE CLASSIFICATION FROM MULTIPLE DEPTH MAPS Pietro Zanuttigh and Ludovico Minto Department of Information Engineering, University of Padova, Italy ABSTRACT This paper proposes a
More informationMachine Learning With Python. Bin Chen Nov. 7, 2017 Research Computing Center
Machine Learning With Python Bin Chen Nov. 7, 2017 Research Computing Center Outline Introduction to Machine Learning (ML) Introduction to Neural Network (NN) Introduction to Deep Learning NN Introduction
More informationAll You Want To Know About CNNs. Yukun Zhu
All You Want To Know About CNNs Yukun Zhu Deep Learning Deep Learning Image from http://imgur.com/ Deep Learning Image from http://imgur.com/ Deep Learning Image from http://imgur.com/ Deep Learning Image
More informationCS 2750: Machine Learning. Neural Networks. Prof. Adriana Kovashka University of Pittsburgh April 13, 2016
CS 2750: Machine Learning Neural Networks Prof. Adriana Kovashka University of Pittsburgh April 13, 2016 Plan for today Neural network definition and examples Training neural networks (backprop) Convolutional
More informationDynamic Routing Between Capsules
Report Explainable Machine Learning Dynamic Routing Between Capsules Author: Michael Dorkenwald Supervisor: Dr. Ullrich Köthe 28. Juni 2018 Inhaltsverzeichnis 1 Introduction 2 2 Motivation 2 3 CapusleNet
More informationUnified, real-time object detection
Unified, real-time object detection Final Project Report, Group 02, 8 Nov 2016 Akshat Agarwal (13068), Siddharth Tanwar (13699) CS698N: Recent Advances in Computer Vision, Jul Nov 2016 Instructor: Gaurav
More informationDeep Learning for Embedded Security Evaluation
Deep Learning for Embedded Security Evaluation Emmanuel Prouff 1 1 Laboratoire de Sécurité des Composants, ANSSI, France April 2018, CISCO April 2018, CISCO E. Prouff 1/22 Contents 1. Context and Motivation
More informationCode Mania Artificial Intelligence: a. Module - 1: Introduction to Artificial intelligence and Python:
Code Mania 2019 Artificial Intelligence: a. Module - 1: Introduction to Artificial intelligence and Python: 1. Introduction to Artificial Intelligence 2. Introduction to python programming and Environment
More informationTutorial on Keras CAP ADVANCED COMPUTER VISION SPRING 2018 KISHAN S ATHREY
Tutorial on Keras CAP 6412 - ADVANCED COMPUTER VISION SPRING 2018 KISHAN S ATHREY Deep learning packages TensorFlow Google PyTorch Facebook AI research Keras Francois Chollet (now at Google) Chainer Company
More informationTutorial on Machine Learning Tools
Tutorial on Machine Learning Tools Yanbing Xue Milos Hauskrecht Why do we need these tools? Widely deployed classical models No need to code from scratch Easy-to-use GUI Outline Matlab Apps Weka 3 UI TensorFlow
More informationFei-Fei Li & Justin Johnson & Serena Yeung
Lecture 9-1 Administrative A2 due Wed May 2 Midterm: In-class Tue May 8. Covers material through Lecture 10 (Thu May 3). Sample midterm released on piazza. Midterm review session: Fri May 4 discussion
More informationAutomotive 3D Object Detection Without Target Domain Annotations
Master of Science Thesis in Electrical Engineering Department of Electrical Engineering, Linköping University, 2018 Automotive 3D Object Detection Without Target Domain Annotations Erik Linder-Norén and
More informationMIXED PRECISION TRAINING: THEORY AND PRACTICE Paulius Micikevicius
MIXED PRECISION TRAINING: THEORY AND PRACTICE Paulius Micikevicius What is Mixed Precision Training? Reduced precision tensor math with FP32 accumulation, FP16 storage Successfully used to train a variety
More informationDeep Learning in Visual Recognition. Thanks Da Zhang for the slides
Deep Learning in Visual Recognition Thanks Da Zhang for the slides Deep Learning is Everywhere 2 Roadmap Introduction Convolutional Neural Network Application Image Classification Object Detection Object
More informationA performance comparison of Deep Learning frameworks on KNL
A performance comparison of Deep Learning frameworks on KNL R. Zanella, G. Fiameni, M. Rorro Middleware, Data Management - SCAI - CINECA IXPUG Bologna, March 5, 2018 Table of Contents 1. Problem description
More informationAn Empirical Study of Generative Adversarial Networks for Computer Vision Tasks
An Empirical Study of Generative Adversarial Networks for Computer Vision Tasks Report for Undergraduate Project - CS396A Vinayak Tantia (Roll No: 14805) Guide: Prof Gaurav Sharma CSE, IIT Kanpur, India
More informationCharacterization and Benchmarking of Deep Learning. Natalia Vassilieva, PhD Sr. Research Manager
Characterization and Benchmarking of Deep Learning Natalia Vassilieva, PhD Sr. Research Manager Deep learning applications Vision Speech Text Other Search & information extraction Security/Video surveillance
More informationDeep learning for dense per-pixel prediction. Chunhua Shen The University of Adelaide, Australia
Deep learning for dense per-pixel prediction Chunhua Shen The University of Adelaide, Australia Image understanding Classification error Convolution Neural Networks 0.3 0.2 0.1 Image Classification [Krizhevsky
More informationReal Time Monitoring of CCTV Camera Images Using Object Detectors and Scene Classification for Retail and Surveillance Applications
Real Time Monitoring of CCTV Camera Images Using Object Detectors and Scene Classification for Retail and Surveillance Applications Anand Joshi CS229-Machine Learning, Computer Science, Stanford University,
More informationCIS680: 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 informationDeep Learning and Its Applications
Convolutional Neural Network and Its Application in Image Recognition Oct 28, 2016 Outline 1 A Motivating Example 2 The Convolutional Neural Network (CNN) Model 3 Training the CNN Model 4 Issues and Recent
More informationDeep Aggregation of Local 3D Geometric Features for 3D Model Retrieval
FURUYA AND OHBUCHI: DEEP AGGREGATION OF LOCAL 3D FEATURES 1 Deep Aggregation of Local 3D Geometric Features for 3D Model Retrieval Takahiko Furuya 1 takahikof AT yamanashi.ac.jp Ryutarou Ohbuchi 1 ohbuchi
More informationDeep 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 informationA Network Architecture for Point Cloud Classification via Automatic Depth Images Generation
A Network Architecture for Point Cloud Classification via Automatic Depth Images Generation Riccardo Roveri 1, Lukas Rahmann 1, A. Cengiz Öztireli 2, Markus Gross 1 1 Department of Computer Science, ETH
More informationObject Localization, Segmentation, Classification, and Pose Estimation in 3D Images using Deep Learning
Allan Zelener Dissertation Proposal December 12 th 2016 Object Localization, Segmentation, Classification, and Pose Estimation in 3D Images using Deep Learning Overview 1. Introduction to 3D Object Identification
More informationDeep Learning Workshop. Nov. 20, 2015 Andrew Fishberg, Rowan Zellers
Deep Learning Workshop Nov. 20, 2015 Andrew Fishberg, Rowan Zellers Why deep learning? The ImageNet Challenge Goal: image classification with 1000 categories Top 5 error rate of 15%. Krizhevsky, Alex,
More informationAccelerating Convolutional Neural Nets. Yunming Zhang
Accelerating Convolutional Neural Nets Yunming Zhang Focus Convolutional Neural Nets is the state of the art in classifying the images The models take days to train Difficult for the programmers to tune
More informationKnow your data - many types of networks
Architectures Know your data - many types of networks Fixed length representation Variable length representation Online video sequences, or samples of different sizes Images Specific architectures for
More informationA Deeper Look at 3D Shape Classifiers
A Deeper Look at 3D Shape Classifiers Jong-Chyi Su, Matheus Gadelha, Rui Wang, Subhransu Maji University of Massachusetts, Amherst {jcsu,mgadelha,ruiwang,smaji}@cs.umass.edu Abstract. We investigate the
More informationYiqi 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 informationA Deep Learning Approach to Vehicle Speed Estimation
A Deep Learning Approach to Vehicle Speed Estimation Benjamin Penchas bpenchas@stanford.edu Tobin Bell tbell@stanford.edu Marco Monteiro marcorm@stanford.edu ABSTRACT Given car dashboard video footage,
More information