A U-Net Based Discriminator for Generative Adversarial ...

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

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.

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

Guidelines for Qualification of Agricultural Land in ...

In 2001, the Legislature passed H .B . 3123, requiring the Tex - as Parks and Wildlife Department (TPWD) to develop and . the Comptroller to adopt rules for the qualification of agricul-tural land in wildlife management use . These guidelines and Chapter 9, Subchapter F of the Texas Administrative Code

  Ultra

SAND, SILT and CLAY - Michigan State University

loam soil. Table 2 lists several tex-tural class names and a typical particle size distribution for each. Some confusion occurs between the use of these terms by many turf managers and the soil scientist. The soil scientist considers the name loam or clay to refer to a range of particle sizes in a soil. The turf manager often refers to a loam as a

  Ultra, Lists, Clay, Tex tural

Wavelet-SRNet: A Wavelet-Based CNN for Multi-Scale Face ...

resolution images [18]. It can depict the contextual and tex-tural information of an image at different levels, which mo-tivatesustointroduceWTtoaCNN-basedsuper-resolution system. As illustrated in Figure 1, the approximation coef-ficients(i.e. the top-left patches in (b-d)) of different-level waveletpacketdecomposition[4]compresstheface’sglob-

  Based, Ultra, Ernst, Wavelet, Tex tural, Wavelet srnet, A wavelet based

100 Conceptos básicos de Astronomía - sea-astronomia.es

tural de nuestra sociedad. Las cosas han cambiado hasta tal pun-to que en la actualidad se está empezando a tener en cuenta en el currículum de un científico las actividades de divulgación que haya realizado. La divulgación se está convirtiendo en la manera que tenemos de aportar nuestro granito de arena a la mejora in-

  Ultra, Isco, Conceptos, 237 a, Astronom, 100 conceptos b, 225 sicos de astronom

AP-197 Dyed Diesel Fuel End User Signed Statement …

istration and identification of any individual affected by applicable law. 42 U.S.C. §405(c)(2)(C)(i); Tex. Govt. Code §§403.011 and 403.078. Release of information on this form in response to a public information request will be governed by the Public Information Act, Chapter 552, Government Code, and applicable federal law.