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

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

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

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

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

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.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE …

ing. Our multi-scale (resolution) fusion module resembles the two pooling modules. The differences include: (1) Our fusion outputs four-resolution representations other than only one, and (2) our fusion modules are repeated several times which is inspired by deep fusion [129], [143], [155], [178], [184]. Our approach. Our network connects high ...

  Multi, Network, Scale, Fusion

Multi-Scale Boosted Dehazing Network With Dense Feature …

Multi-scale feature fusion. Feature fusion has been widely used in the network design for performance gain by exploit-ing features from different layers. Numerous image restora-tion methods fuse features by using dense connection [61], feature concatenation [64] or weighted element-wise sum-mation [9, 62]. Most existing feature fusion modules reuse

  Multi, Network, Scale, Fusion

JOURNAL OF LA DS-TransUNet: Dual Swin Transformer U-Net ...

tract multi-scale features for image classification. Multi Vision Transformers (MViT) [22] is present for video and image recognition by connecting multi-scale feature hierarchies with transformer models. Multi-modal Multi-scale TRansformer (M2TR) [23] uses a multi-scale transformer to detect the local inconsistency at different scales.

  Multi, Scale

PROJECTS FLOATED FOR JULY 2022 INTAKE

Adaptive Network Traffic Signal Control Systems using machine learning 45 IMURA1001 (5) Modelling heterogeneous non-lane based traffic flow: microscopic vs macroscopic approach 46 IMURA1003 (3) Reasoning about Resource-Bounded Multi-Agent Systems 47 IMURA1004 (5) Development of Integrated Health Monitoring System for

  Multi, Network

AAAI-20 Accepted Paper List.3.23.20docx

Yu.Ming!Shang!(Bit)*;!Heyan!Huang!(Beijing!Engineering!Research!Center!of!High!Volume!Language!Information Processing!and!Cloud!Computing!Applications,!Department!of ...