SuperPoint: Self-Supervised Interest Point Detection and ...

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

Learning Deep Features for Discriminative Localization

weights of the output layer on to the convolutional feature maps, a technique we call class activation mapping. As illustrated in Fig. 2, global average pooling outputs the spatial average of the feature map of each unit at the last convolutional layer. A weighted sum of these values is used to generate the final output. Similarly, we compute a

  Feature, Deep, Activation, Convolutional, Convolutional features

Image Style Transfer Using Convolutional Neural Networks

cent advance of Deep Convolutional Neural Networks [18] ... tent in generic feature representations that generalise across datasets [6] and even to other visual information processing tasks [19, 4, 2, 9, 23], including texture recognition [5] and ... ij is the activation of the ith filter at position j in layer l.

  Feature, Styles, Generic, Transfer, Deep, Activation, Convolutional, Deep convolutional, Style transfer, Generic feature

Siamese Neural Networks for One-shot Image Recognition

between the twin feature vectors h 1 and h 2 combined with a sigmoid activation, which maps onto the interval [0;1]. Thus a cross-entropy objective is a natural choice for train-ing the network. Note that in LeCun et al., they directly learned the similarity metric, which was implictly defined by the energy loss, whereas we fix the metric as ...

  Feature, Activation

Squeeze-and-Excitation Networks

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-

  Convolutional

DeCAF: A Deep Convolutional Activation Feature for …

DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition (a) LLC (b) GIST (c) DeCAF 1 (d) DeCAF 6 Figure 1. This figure shows several t-SNE feature visualizations on the ILSVRC-2012 validation set. (a) LLC , (b) GIST, and features derived from our CNN: (c) DeCAF 1, the first pooling layer, and (d) DeCAF

  Feature, Generic, Deep, Activation, Convolutional, A deep convolutional activation feature for, A deep convolutional activation feature for generic

ABSTRACT arXiv:1409.1556v6 [cs.CV] 10 Apr 2015

arXiv:1409.1556v6 [cs.CV] 10 Apr 2015 Published as a conference paper at ICLR 2015 VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION Karen Simonyan∗ & Andrew Zisserman+ Visual Geometry Group, Department of Engineering Science, University of Oxford

  Deep, Convolutional, Deep convolutional

SuperPoint: Self-Supervised Interest Point Detection and ...

coder consists of convolutional layers, spatial downsam-pling via pooling and non-linear activation functions. Our encoder uses three max-pooling layers, letting us define H c = H=8 and W c = W=8 for an image sized H W. We refer to the pixels in the lower dimensional output as “cells,” where three 2 2 non-overlapping max pooling op-

  Activation, Convolutional, Superpoint

Deep Image Prior - CVF Open Access

mation contained within the activations of deep neural net-works. For this, we consider the “natural pre-image” tech-nique of [21], whose goal is to characterize the invariants learned by a deep network by inverting it on the set of nat-ural images. …

  Deep, A deep

Delving Deep into Rectifiers: Surpassing Human-Level ...

method for deep rectifier networks (Sec. 2.2). 2.1. Parametric Rectifiers We show that replacing the parameter-free ReLU by a learned activation unit improves classification accuracy2. Definition. Formally, we define an activation function: f(yi)= yi, if yi > 0 aiyi, if yi ≤ 0. (1) Here yi is the input of the nonlinear activation f on ...

  Deep, Activation