Explainability Methods for Graph Convolutional Neural …

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

Digital Signal Processing - INAOE - P

4.1 Discrete Fourier Transform 87 4.1.1 Fourier Series Coefficients of Periodic Digital Signals 88 4.1.2 Discrete Fourier Transform Formulas 92 4.2 Amplitude Spectrum and Power Spectrum 98 4.3 Spectral Estimation Using Window Functions 110 4.4 Application to Speech Spectral Estimation 117 4.5 Fast Fourier Transform 120

  Fourier, Spectral

Digital Signal Processing

Digital signal processing Analog/digital and digital/analog converter, CPU, DSP, ASIC, FPGA. Advantages: → noise is easy to control after initial quantization → highly linear (within limited dynamic range) → complex algorithms fit into a single chip → flexibility, parameters can easily be varied in software → digital processing is insensitive to component tolerances, aging,

  Processing, Signal, Digital, Digital signal processing

NUMERICAL RECIPES - Assets

CAMBRIDGE UNIVERSITY PRESS Cambridge, New York, Melbourne, Madrid, Cape Town, Singapore, S˜ao Paulo Cambridge University Press 32 Avenue of the Americas, New York, NY 10013-2473, USA

  Numerical, Recipes, Numerical recipes

Probability, Statistics, and Random Processes for ...

4.6 The Markov and Chebyshev Inequalities 181 4.7 Transform Methods 184 4.8 Basic Reliability Calculations 189 4.9 Computer Methods for Generating Random Variables 194 4.10 Entropy 202 Summary 213 Problems 215 CHAPTER 5 Pairs of Random Variables 233 5.1 Two Random Variables 233 5.2 Pairs of Discrete Random Variables 236 5.3 The Joint cdf of X ...

  Methods, Chebyshev

An End-to-End Deep Learning Architecture for Graph ...

by graph Fourier transform. This transformation involves expensive multiplications with the eigenvector matrix of the graph Laplacian. To reduce the computation burden, (Def-ferrard, Bresson, and Vandergheynst 2016) parameterized the spectral filters as Chebyshev polynomials of eigenvalues, and achieved efficient and localized filters.

  Architecture, Learning, Deep, Graph, Fourier, Spectral, Chebyshev, To end deep learning architecture for graph

Geometric Deep Learning on Graphs and Manifolds Using ...

Chebyshev Spectral CNN (ChebNet). In order to allevi-ate the cost of explicitly computing the graph Fourier trans-form,Defferrardetal.[13]usedanexplicitexpansioninthe Chebyshev polynomial basis to represent the spectral filters gα(∆) = rX−1 j=0 αjTj(∆˜ ) = rX−1 j=0 αjΦTj(Λ˜)Φ⊤, (4) where ∆˜ = 2λ−1

  Fourier, Spectral, Chebyshev, Chebyshev spectral