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

Deep Domain Confusion: Maximizing for Domain Invariance

can be trained for supervised adaptation, when there is a small amount of target labels available, or unsupervised adaptation, when no target labels are available. We intro-duce domain invariance through domain confusion guided selection of the depth and width of the adaptation layer, as well as an additional domain loss term during fine-tuning

  Deep, Maximizing, Confusion, Adaptation, Domain, Unsupervised, Invariance, Unsupervised adaptation, Deep domain confusion, Maximizing for domain invariance

Learning Transferable Features with Deep Adaptation Networks

Deep Adaptation Networks In unsupervised domain adaptation, we are given a source domainDs = {(xs i,y s i)} ns i=1 withns labeledexamples,and a target domain Dt = {xt j} nt j=1 with nt unlabeled exam-ples. The source domain and target domain are charac-terized by probability distributions p and q, respectively.

  Adaptation, Unsupervised

PSD: Principled Synthetic-to-Real Dehazing Guided by ...

2.2. Unsupervised Domain Adaptation Unsupervised domain adaptation aims to tackle domain shift between source and target domains, while images in the target domain are unlabeled. One major idea is to in-duce alignment between the source and target domains in feature space by optimizing for some measurements of dis-tributional discrepancy [23 ...

  Adaptation, Unsupervised, Unsupervised adaptation

Internal Audit: Key risk areas 2021

circumvented when employees are unsupervised, as they are often overlooked and ignored to save time. Advancements of technology also increase the sophistication and frequency of cyber security attacks and frauds. Internal Audit can offer its view on the extent to which any relaxing or adaptation of controls has

  Internal, Audit, Adaptation, Internal audit, Unsupervised

Guidance on the Use of Antipsychotics

Lester UK Adaptation – Positive Cardiometabolic Health Resource 51 Appendix 7 Drugs known to prolong QT interval 54 Appendix 8 References ... who are unsupervised For non-adherent patients who are supervised Change to an alternative depot medication or other long-acting

  Adaptation, Unsupervised

WIPO Technology Trends 2019: Artificial Intelligence

“unsupervised learning” – learning without labelled data – remains a holy grail of AI. Even without this “holy grail,” AI is already creating massive economic value in the world today. In covering AI, the media tends to focus on images, speech and natural language processing because those types of data are very human.

  Technology, Trends, Wipo, Unsupervised, Wipo technology trends

AAAI-21 Accepted Paper List.1.29

! 4!! 228:!Rain!Streak!Removal!via!Dual!Graph!Convolutional!Network! Xueyang!Fu,!Qi!Qi,!Yurui!Zhu,!Xinghao!Ding,!Zheng*Jun!Zha!! 233:!RevMan:!Revenue*Aware!Multi*Task ...