Class-Balanced Loss Based on Effective Number of Samples

and large-scale datasets including ImageNet and iNatural-ist. Our results show that when trained with the proposed class-balanced loss, the network is able to achieve signifi-cant performance gains on long-tailed datasets. 1. Introduction The recent success of deep Convolutional Neural Net-works (CNNs) for visual recognition [26, 37, 38, 16] owes

  Scale, Visual, Recognition, Visual recognition

PointNet: Deep Learning on Point Sets ... - CVF Open Access

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation Charles R. Qi* Hao Su* Kaichun Mo Leonidas J. Guibas Stanford University

  Open, Learning, Points, Deep, Sets, Pointnet, Deep learning on point sets

RegularFace: Deep Face Recognition via Exclusive ...

RegularFace: Deep Face Recognition via Exclusive Regularization Kai Zhao Jingyi Xu Ming-Ming Cheng ∗ TKLNDST, CS, Nankai University kaiz.xyz@gmail.com cmm@nankai.edu.cn

  Zhao

Finding Tiny Faces in the Wild With Generative Adversarial ...

faces, which are unfriendly for the face classifier. Toward-s this end, we design a refinement sub-network to recover some detailed information. In the discriminator network, the basic GAN [17, 12, 8] is trained to distinguish the real and fake high resolution images. To classify faces or non-

  Faces

Auto-DeepLab: Hierarchical Neural Architecture Search for ...

Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation Chenxi Liu1∗, Liang-Chieh Chen 2, Florian Schroff2, Hartwig Adam2, Wei Hua2, Alan Yuille1, Li Fei-Fei3 1Johns Hopkins University 2Google 3Stanford University Abstract Recently, NeuralArchitectureSearch(NAS)hassuccess-

What Have We Learned From Deep Representations for …

what these powerful models actually have learned. In this paper we shed light on deep spatiotemporal net-works by visualizing what excites the learned models us-ing activation maximization by backpropagating on the in-put. We are the first to visualize the hierarchical features

  What, Have, Learned, What we have learned, Have learned

Squeeze-and-Excitation Networks - openaccess.thecvf.com

Squeeze-and-Excitation Networks Jie Hu1∗ Li Shen2∗ Gang Sun1 hujie@momenta.ai lishen@robots.ox.ac.uk sungang@momenta.ai 1 Momenta 2 Department of Engineering Science, University of Oxford Abstract Convolutional neural networks are built upon the con-

  Network, Excitation, Squeeze and excitation networks, Squeeze

Protecting World Leaders Against Deep Fakes

Protecting World Leaders Against Deep Fakes Shruti Agarwal and Hany Farid University of California, Berkeley Berkeley CA, USA {shrutiagarwal, hfarid}@berkeley.edu

Frustum PointNets for 3D Object Detection From RGB-D Data

Frustum PointNets for 3D Object Detection from RGB-D Data Charles R. Qi1∗ Wei Liu2 Chenxia Wu2 Hao Su3 Leonidas J. Guibas1 1Stanford University 2Nuro, Inc. 3UC San Diego Abstract In this work, we study 3D object detection from RGB-D data in both indoor and outdoor scenes.

ESRGAN: Enhanced Super-Resolution Generative Adversarial ...

ESRGAN: EnhancedSuper-Resolution Generative Adversarial Networks Xintao Wang 1, Ke Yu , Shixiang Wu2, Jinjin Gu3, Yihao Liu4, Chao Dong 2, Yu Qiao , and Chen Change Loy5 1 CUHK-SenseTime Joint Lab, The Chinese University of Hong Kong 2 Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences 3 The Chinese University of Hong Kong, …

  Network, Adversarial, Generative, Generative adversarial, Generative adversarial networks

Deep Residual Learning for Image Recognition

the residual learning principle is generic, and we expect that it is applicable in other vision and non-vision problems. 2. Related Work Residual Representations. In image recognition, VLAD [18] is a representation that encodes by the residual vectors with respect to a dictionary, and Fisher Vector [30] can be

  Image, Learning, Residual, Recognition, Residual learning for image recognition, Image recognition, Residual learning

Deep Residual Learning for Image Recognition

the residual learning principle is generic, and we expect that it is applicable in other vision and non-vision problems. 2. Related Work Residual Representations. In image recognition, VLAD [18] is a representation that encodes by the residual vectors with respect to a dictionary, and Fisher Vector [30] can be

  Image, Learning, Residual, Recognition, Residual learning for image recognition, Image recognition, Residual learning

A Closer Look at Spatiotemporal Convolutions for Action ...

residual learning, which has been shown to be a powerful tool in the field of still-image recognition. We demonstrate that 3D ResNets significantly outperform 2D ResNets for the same depth when trained and evaluated on large-scale, challenging action recognition benchmarks such as Sports-1M [16] and Kinetics [17].

  Image, Learning, Residual, Recognition, Image recognition, Residual learning

Faster R-CNN: Towards Real-Time Object Detection with ...

oped for learning segmentation proposals. Shared computation of convolutions [9], [1], [29], [7], [2] has been attracting increasing attention for ef-ficient, yet accurate, visual recognition. The OverFeat paper [9] computes convolutional features from an image pyramid for …

  Image, Learning, Recognition, Faster, Faster r cnn

arXiv:1812.01187v2 [cs.CV] 5 Dec 2018

initial learning rate is , then at batch i, 1 i m, we will set the learning rate to be i =m. Zero . A ResNet network consists of multiple residual blocks, each block consists of several convolutional lay-ers. Given input x, assume block(x) is the output for the last layer in the block, this residual block then outputs x+ block(x).

  Learning, Residual

ImageNet Classification with Deep Convolutional Neural …

Current approaches to object recognition make essential use of machine learning methods. To im-prove their performance, we can collect larger datasets, learn more powerful models, and use bet-ter techniques for preventing overfitting. Until recently, datasets of …

  Learning, Recognition

Aggregated Residual Transformations for Deep Neural …

Aggregated Residual Transformations for Deep Neural Networks Saining Xie1 Ross Girshick2 Piotr Dollar´ 2 Zhuowen Tu1 Kaiming He2 1UC San Diego 2Facebook AI Research {s9xie,ztu}@ucsd.edu {rbg,pdollar,kaiminghe}@fb.com Abstract We present a simple, highly modularized network archi-tecture for image classification. Our network is constructed

  Image, Residual, For image

Wide Residual Networks arXiv:1605.07146v4 [cs.CV] 14 Jun ...

Figure 1: Various residual blocks used in the paper. Batch normalization and ReLU precede each convolution (omitted for clarity) [28], which is an architecture that had been proposed prior to residual networks. The essen-tial difference between residual and highway networks is that in the latter residual links are

  Residual

Residual Attention Network for Image Classification

Residual Attention Network for Image Classification Fei Wang1, Mengqing Jiang2, Chen Qian1, Shuo Yang3, Cheng Li1, Honggang Zhang4, Xiaogang Wang3, Xiaoou Tang3 1SenseTime Group Limited, 2Tsinghua University, 3The Chinese University of Hong Kong, 4Beijing University of Posts and Telecommunications 1{wangfei, qianchen, chengli}@sensetime.com, …

  Image, Residual, For image