Exploring Cross-Image Pixel Contrast for Semantic …

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

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

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

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

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.

Collaborative Knowledge Base Embedding for Recommender …

network embedding method, termed as TransR, to extract items’ structural representations by considering the heterogeneity of both nodes and relationships. We apply stacked denoising auto-encoders and stacked convolutional auto-encoders, which are two types of deep learning based embedding techniques, to extract items’ tex-

  Network, Structural, Deep, Embedding, Network embedding

Structural Deep Network Embedding - SIGKDD

network structure well and are robust to sparse networks. In summary, the contributions of this paper are listed as follows: We propose a Structural Deep Network Embedding method, namely SDNE, to perform network embedding. The method is able to map the data to a highly non-linear latent space to preserve the network structure and is robust to ...

  Network, Structural, Deep, Embedding, Structural deep network embedding, Network embedding

Deep Learning on Graphs - Michigan State University

4.2.2 Preserving Structural Role 86 4.2.3 Preserving Node Status 89 ... ing traditional graph embedding, modern graph embedding, and deep learn-ing on graphs. As the first generation of graph representation learning, tra- ... social network analysis, GNNs result in state-of-the-art performance and bring

  Network, Learning, Structural, Learn, Deep, Graph, Embedding, Deep learning on graphs, Deep learn ing on graphs

Heterogeneous Graph Neural Network

neural network architecture with two modules to aggregate feature information of those sampled neighboring nodes. The first module encodes “deep” feature interactions of heterogeneous contents and generates content embedding for each node. The second module aggregates content (attribute) embeddings of different neighboring

  Network, Deep, Embedding, Heterogeneous

Representation Learning on Graphs: Methods and Applications

encoding structural information about a graph (e.g., degree statistics or kernel functions). However, recent years have seen a surge in approaches that automatically learn to encode graph structure into low-dimensional embeddings, using techniques based on deep learning and nonlinear dimensionality reduction.

  Learning, Structural, Deep, Graph, Deep learning

DeepWalk: Online Learning of Social Representations

is used on Zachary’s Karate network [44] to generate a la-tent representation in R2. Note the correspondence between community structure in the input graph and the embedding. Vertex colors represent a modularity-based clustering of the input graph. 1. INTRODUCTION The sparsity of a network representation is both a strength and a weakness.

  Network, Embedding, Deepwalk

DeepWalk: Online Learning of Social Representations

network classi cation tasks for social networks such as Blog-Catalog, Flickr, and YouTube. Our results show that Deep-Walk outperforms challenging baselines which are allowed a global view of the network, especially in the presence of missing information. DeepWalk’s representations can pro-vide F 1 scores up to 10% higher than competing methods

  Network, Deep

arXiv:1706.02216v4 [cs.SI] 10 Sep 2018

inductive node embedding. Unlike embedding approaches that are based on matrix factorization, we leverage node features (e.g., text attributes, node profile information, node degrees) in order to learn an embedding function that generalizes to unseen nodes. By incorporating node features in the

  Embedding

A Survey on Heterogeneous Graph Embedding: Methods ...

embedding (i.e., heterogeneous graph representation learn-ing), aiming to learn a function that maps input space into a lower-dimension space while preserving the hetero-geneous structure and semantics, has drawn considerable attentions in recent years. Although there have been ample studies of embedding technology on homogeneous graphs

  Embedding