SDSEN: Self-Refining Deep Symmetry Enhanced Network

Slides:



Advertisements
Similar presentations
Tiled Convolutional Neural Networks TICA Speedup Results on the CIFAR-10 dataset Motivation Pretraining with Topographic ICA References [1] Y. LeCun, L.
Advertisements

Hurieh Khalajzadeh Mohammad Mansouri Mohammad Teshnehlab
Video Tracking Using Learned Hierarchical Features
Deep Convolutional Nets
Skeleton Based Action Recognition with Convolutional Neural Network
Zuxuan Wu, Xi Wang, Yu-Gang Jiang, Hao Ye, Xiangyang Xue
CSC321: 2011 Introduction to Neural Networks and Machine Learning Lecture 6: Applying backpropagation to shape recognition Geoffrey Hinton.
Deep Residual Learning for Image Recognition
Parsing Natural Scenes and Natural Language with Recursive Neural Networks INTERNATIONAL CONFERENCE ON MACHINE LEARNING (ICML 2011) RICHARD SOCHER CLIFF.
Facial Smile Detection Based on Deep Learning Features Authors: Kaihao Zhang, Yongzhen Huang, Hong Wu and Liang Wang Center for Research on Intelligent.
Deeply-Recursive Convolutional Network for Image Super-Resolution
Wenchi MA CV Group EECS,KU 03/20/2017
Recent developments in object detection
Big data classification using neural network
Deep Learning for Dual-Energy X-Ray
Learning to Compare Image Patches via Convolutional Neural Networks
Demo.
Compact Bilinear Pooling
Cascade of multi-scale convolutional neural networks for bone suppression of chest radiographs in gradient domain  Yang Wei , Chen Yingyin , Liu Yunbi.
Convolutional Neural Fabrics by Shreyas Saxena, Jakob Verbeek
Saliency-guided Video Classification via Adaptively weighted learning
Jure Zbontar, Yann LeCun
A Neural Approach to Blind Motion Deblurring
Yun-FuLiu Jing-MingGuo Che-HaoChang
Classification of Hand-Written Digits Using Scattering Convolutional Network Dongmian Zou Advisor: Professor Radu Balan.
Training Techniques for Deep Neural Networks
CS6890 Deep Learning Weizhen Cai
Disguised Face Identification (DFI) with Facial KeyPoints using Spatial Fusion Convolutional Network Nathan Sun CIS601.
Computer Vision James Hays
SBNet: Sparse Blocks Network for Fast Inference
Wei Liu, Chaofeng Chen and Kwan-Yee K. Wong
Convolutional Neural Networks for Visual Tracking
Towards Understanding the Invertibility of Convolutional Neural Networks Anna C. Gilbert1, Yi Zhang1, Kibok Lee1, Yuting Zhang1, Honglak Lee1,2 1University.
Deep Learning Hierarchical Representations for Image Steganalysis
Object Detection + Deep Learning
8-3 RRAM Based Convolutional Neural Networks for High Accuracy Pattern Recognition and Online Learning Tasks Z. Dong, Z. Zhou, Z.F. Li, C. Liu, Y.N. Jiang,
Single Image Rolling Shutter Distortion Correction
MEgo2Vec: Embedding Matched Ego Networks for User Alignment Across Social Networks Jing Zhang+, Bo Chen+, Xianming Wang+, Fengmei Jin+, Hong Chen+, Cuiping.
CornerNet: Detecting Objects as Paired Keypoints
Noah Snavely.
KFC: Keypoints, Features and Correspondences
Use 3D Convolutional Neural Network to Inspect Solder Ball Defects
Outline Background Motivation Proposed Model Experimental Results
RCNN, Fast-RCNN, Faster-RCNN
Iterative Crowd Counting
View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictions 1,2 1.
Convolutional Neural Networks
Textual Video Prediction
Heterogeneous convolutional neural networks for visual recognition
FOCUS PRIOR ESTIMATION FOR SALIENT OBJECT DETECTION
Abnormally Detection
Neural Architecture Search: Basic Approach, Acceleration and Tricks
LOGAN: Unpaired Shape Transform in Latent Overcomplete Space
Chuan Wang1, Haibin Huang1, Xiaoguang Han2, Jue Wang1
Human-object interaction
Rotational Rectification Network (R2N):
Learning and Memorization
Unrolling the shutter: CNN to correct motion distortions
Introduction to Artificial Intelligence Lecture 22: Computer Vision II
Weak-supervision based Multi-Object Tracking
Deep Structured Scene Parsing by Learning with Image Descriptions
End-to-End Facial Alignment and Recognition
Peng Cui Tsinghua University
Week 3 Volodymyr Bobyr.
Bidirectional LSTM-CRF Models for Sequence Tagging
Eliminating Background-Bias for Robust Person Re-identification
Deep Video Quality Assessor: From Spatio-temporal Visual Sensitivity to A convolutional Neural Aggregation Network Woojae Kim1, Jongyoo Kim2, Sewoong Ahn1,Jinwoo.
Computing the Stereo Matching Cost with a Convolutional Neural Network
CVPR2019 Jiahe Li SiamRPN introduces the region proposal network after the Siamese network and performs joint classification and regression.
Shengcong Chen, Changxing Ding, Minfeng Liu 2018
Presentation transcript:

SDSEN: Self-Refining Deep Symmetry Enhanced Network for Rain Removal Hong Liu, Hanrong Ye*, Xia Li, Wei Shi, Mengyuan Liu, Qianru Sun Key Laboratory of Machine Perception, Peking University, China *Corresponding Author: leoyhr@pku.edu. CODE: https://github.com/prismformore/SDSEN Please STAR and FORK! INTRODUCTION Ⅰ Group Equivariant Convolution Ⅳ EXPERIMENTAL RESULTS Ⅵ A family of symmetry enhanced CNNs theoretically designed with rotation equivariance. Mathematically, regular convolution could be formulated as: G-convolution is formulated as: here g denotes a symmetry transformation (e.g. rotation, translation). Transformation g of group p4 could be decomposed into a translation t and a rotation s : g = ts. Therefore, G-convolution could be rewritten as: Thus, to compute the p4 G-convolution we can first compute filter transformation for all 4 rotations, and then call a regular convolution routine on ƒ and the augmented filter bank. Symmetry enhanced convolutional block P4 G-convolution composes of two types: p4 G-Convolution on Z2 (P4ConvZ2) and p4 G-convolution on p4 (P4ConvP4). Symmetry aggregation block We propose to apply a 5 × 5 convolution on all orientation channels of G-feature maps to avoid the information loss of pooling. Ablation Study Comparisons with state-of-arts As a natural phenomenon, rain degenerates the visibility of images and affects vision algorithms severely. By restoring background information in rain scenes, rain removal is helpful for many computer vision systems including autonomous driving, intelligent photography and surveillance camera. OBSERVATION AND CONTRIBUTION Ⅱ The state-of-the-art methods are mostly based on Convolutional Neural Network (CNN). However, as CNN is not equivariant to object rotation, these methods are unsuitable for dealing with the tilted rain streaks. Contribution: We propose Deep Symmetry Enhanced Network (DSEN), which is able to explicitly extract the rotation equivariant features from rain images. The overlapping rain streaks make rain removal difficult to remove at a glance. Contribution: We design a self-refining mechanism to remove the accumulated rain streaks in a coarse-to-fine manner. This mechanism reuses DSEN with a novel information link which passes the gradient flow to the higher stages. PIPELINE OF IMPROVED PERSON SEARCH NETWORK Ⅲ REFERENCES Ⅶ DATASETS Ⅴ [1] Hong Liu et al., “Self-Refining Deep Symmetry Enhanced Network”, in ICIP, 2019, pp. 2786-2790. [2] Taco S. Cohen et al., “Group equivariant convolutional networks,” in ICML, 2016, pp. 2990– 2999. [3] Wenhan Yang et al., “Deep joint rain detection and removal from a single image,” in CVPR, 2017, pp. 1357–1366. [4] He Zhang et al., “Image de-raining using a conditional generative adversarial network,” arXiv preprint arXiv:1701.05957,2017. The statistics of the Rain100H and Zhang800 datasets. Dataset Images Training Set Testing Set Rain100H 1900 1800 100 Zhang800 800 700 A two-stage example of Self-refining DSEN. The output of stage I (O´) is reused as the input of stage II. P4ConvZ2 (yellow) contains one filter with four rotations (corresponding to 90°, 180°, 270° and 360°). P4ConvP4 (blue) contains four filters with four rotations.