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

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

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

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

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

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-

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

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.

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

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

A Simple Framework for Contrastive Learning of Visual ...

• A contrastive loss function defined for a contrastive pre-diction task. Given a set fx~ kgincluding a positive pair of examples x~ iand x~ j, the contrastive prediction task aims to identify x~ jin fx~ kg k6=ifor a given x~ i. We randomly sample a minibatch of Nexamples and define the contrastive prediction task on pairs of augmented exam-

  Framework, Learning, Simple, Visual, Contrastive, Simple framework for contrastive learning of visual

Understanding Contrastive Representation Learning through ...

The term contrastive loss has also been generally used to refer to various objectives based on positive and negative samples, e.g., in Siamese networks (Chopra et al., 2005; Hadsell et al., 2006). In this work, we focus on the spe-cific form in Equation (1) that is widely used in modern unsupervised contrastive representation learning literature.

  Contrastive

DetCo: Unsupervised Contrastive Learning for Object Detection

contrastive learning [5,19,5,3,18] currently achieved state-of-the-art performance, arousing extensive attention from researchers. Unlike generative methods, contrastive learning avoids the computation-consuming generation step by pulling representations of different views of the same im-age (i.e., positive pairs) close, and pushing representations

  Contrastive

Exploring Simple Siamese Representation Learning

Contrastive learning. The core idea of contrastive learn-ing [16] is to attract the positive sample pairs and repulse the negative sample pairs. This methodology has been recently popularized for un-/self-supervised representation learning [36,30,20,37,21,2,35,17,29,8,9]. Simple and effective instantiations of contrastive learning have been ...

  Learning, Simple, Representation, Contrastive, Assieme, Simple siamese representation learning

Bootstrap Your Own Latent A New Approach to Self ...

Contrastive approaches avoid a costly generation step in pixel space by bringing representation of different views of the same image closer (‘positive pairs’), and spreading representations of views from different images (‘negative pairs’) apart [39, 40]. Contrastive methods often require

  Your, Talent, Bootstrap, Contrastive, Bootstrap your own latent

Mother-Tongue Interference in the Acquisition of English ...

Contrastive analysis is concerned with the study of a pair of languages with the aim of discovering their structural similarities and differences. Contrastive Analysis is a method that was widely used in the 1960s and early 1970s to explain why some features of a target language were more difficult to learn than others. (Mozlan, 2015)

  Contrastive

Supervised Contrastive Learning - NIPS

contrastive learning which uses only a single positive). These positives are drawn from samples of the same class as the anchor, rather than being data augmentations of the anchor, as done in self-supervised learning. While this is a simple extension to the self-supervised setup, it is non-

  Contrastive

Self-Prediction and Contrastive Learning

Contrastive Learning: Inter-Sample Classification Given both similar (“positive”) and dissimilar (“negative”) candidates, to identify which ones are similar to the anchor data point is a classification task. There are creative ways to construct a set of data point candidates: 1. The original input and its distorted version

  Contrastive

Dimensionality Reduction by Learning an Invariant Mapping

A contrastive loss function is employed to learn the param-eters W of a parameterizedfunction GW, in such a way that neighborsare pulled togetherand non-neighborsare pushed apart. Priorknowledgecan beused to identifythe neighbors for each training data point. The method uses an energy based model that uses the

  Reduction, Learning, Contrastive, Dimensionality, Dimensionality reduction by learning an