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

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.

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

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-

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

PredRNN: Recurrent Neural Networks for Predictive Learning ...

learning methods [19, 21, 6, 12, 25] focus more on modeling temporal variations (such as the object moving trajectories), with memory states being updated repeatedly over time inside each LSTM unit. Admittedly, the stacked LSTM architecture is proved powerful for supervised spatiotemporal learning Corresponding author: Mingsheng Long

  Time, Learning, Temporal

System Initiative on Shaping the Future of Production ...

potential transformations and disruptions in the entire world of suppliers, customers and adjacent markets. ... The resulting greater spatial and temporal flexibility brought about by technology will bring locations of production and ... devices in real time, are but some case examples of IoT applications. Smart enterprise control, asset ...

  Time, Transformation, Temporal

Learning Disabilities: Characteristics and Instructional ...

Inadequate temporal concepts-Disoriented in time. Academic Disabilities Problems in reading, writing spelling and arithmetic. Every learning disabled child does not exhibit all the above characteristics, rather each demonstrate a unique combination of these characteristics.

  Time, Learning, Temporal

Inductive Representation Learning on Large Graphs - …

to orthogonal transformations of the embeddings, which means that the embedding space does not naturally generalize between graphs and can drift during re-training. One notable exception to this trend is the Planetoid-I algorithm introduced by Yang et al. [40], which is an inductive, embedding-based approach to semi-supervised learning.

  Large, Transformation, Learning, Representation, Inductive, Graph, Inductive representation learning on large graphs

InfoGAN: Interpretable Representation Learning by ... - NIPS

supervised learning: bilinear models [18] separate style and content; multi-view perceptron [19] separate face identity and view point; and Yang et al. [20] developed a recurrent variant that generates a sequence of latent factor transformations. Similarly, VAEs [5] and Adversarial Autoencoders [9]

  Transformation, Learning

InfoGAN: Interpretable Representation Learning ... - arxiv.org

supervised learning: bilinear models [21] separate style and content; multi-view perceptron [22] separate face identity and view point; and Yang et al. [23] developed a recurrent variant that generates a sequence of latent factor transformations. Similarly, VAEs [5] and Adversarial Autoencoders [9]

  Transformation, Learning

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

to orthogonal transformations of the embeddings, which means that the embedding space does not naturally generalize between graphs and can drift during re-training. One notable exception to this trend is the Planetoid-I algorithm introduced by Yang et al. [40], which is an inductive, embedding-based approach to semi-supervised learning.

  Transformation, Learning

Future Frame Prediction for Anomaly Detection - A New …

2.2. Deep Learning Based Methods Deep learning approaches have demonstrated their suc-cesses in many computer vision tasks [12][20] as well as anomaly detection [14]. In the work [40], Xu et al. de-signamulti-layerAuto-Encoderfor feature learning, which demonstrates the effectiveness of deep learning features.

  Learning

A Tutorial on Graph-Based SLAM - uni-freiburg.de

transformations in SE(2) or in SE(3), while the map can be represented in different ways. Maps can be parametrized as a set of spatially located landmarks, by dense representations like occupancy grids, surface maps, or by raw sensor measure-ments. The choice of a particular map representation depends

  Transformation, Slam

Introduction to Quantum Field Theory - Stony Brook …

uncountable approaches of learning it. The idea of these notes initially started during my rst year at Stony Brook University, when I was very well exposed to the subject, during the courses taught by Dr. George Sterman, [STERMAN1993], and by Dr. Dmitri Kharzeev, [KHARZEEV2010] . However, most of the rst part of

  Introduction, Field, Learning, Theory, Quantum, Introduction to quantum field theory