Towards End-to-End License Plate Detection and …

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.

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

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

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

Faster R-CNN: Towards Real-Time Object Detection with ...

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Shaoqing Ren Kaiming He Ross Girshick Jian Sun Microsoft Research fv-shren, kahe, rbg, jiansung@microsoft.com Abstract State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [7] and Fast R ...

  Time, Real, Towards, Object, Detection, Object detection, Towards real time object detection

You Only Look Once: Unified, Real-Time Object Detection

ized sensors, enable assistive devices to convey real-time scene information to human users, and unlock the potential for general purpose, responsive robotic systems. Current detection systems repurpose classifiers to per-form detection. To detect an object, these systems take a classifier for that object and evaluate it at various locations

  Time, Real, Object, Detection, Time object detection

You Only Look Once: Unified, Real-Time Object Detection

ized sensors, enable assistive devices to convey real-time scene information to human users, and unlock the potential for general purpose, responsive robotic systems. Current detection systems repurpose classifiers to per-form detection. To detect an object, these systems take a classifier for that object and evaluate it at various locations

  Time, Real, Object, Detection, Time object detection

Abstract

only having detection data for 44 of the 200 classes. On the 156 classes not in COCO, YOLO9000 gets 16.0 mAP. But YOLO can detect more than just 200 classes; it predicts de-tections for more than 9000 different object categories. And it still runs in real-time. 1. Introduction General purpose object detection should be fast, accu-

  Time, Real, Object, Detection, Object detection

Abstract arXiv:2103.02603v2 [cs.CV] 9 May 2021

knowledge base. This would define a smart object detection system, and ours is an effort towards achieving this goal. The key contributions of our work are: •We introduce a novel problem setting, Open World Object Detection, which models the real-world more closely. •We develop a novel methodology, called ORE, based on

  Real, Towards, Object, Detection, Object detection

EfficientDet: Scalable and Efficient Object Detection

towards more accurate object detection; meanwhile, state-of-the-art object detectors also become increasingly more expensive. For example, the latest AmoebaNet-based NAS-FPN detector [42] requires 167M parameters and 3045B FLOPs (30x more than RetinaNet [21]) to achieve state-of-the-art accuracy. The large model sizes and expensive com-

  Towards, Object, Detection, Object detection

Florence: A New Foundation Model for Computer Vision

cation) to fine-grained (e.g. object detection), 2) Time: from static (e.g. images) to dynamic (e.g. videos), and 3) Modal-ity: from RGB only to multiple senses (e.g. captioning and depth). Due to the diversity nature of visual understanding, we …

  Time, Object, Detection, Object detection

Time of Flight Principles, Challenges, and Performance …

Time of Flight Basics Active illumination system: • Laser emits light (photons) towards a target • Light (partially) reflected from the target • Sensor area determines when light (photons) arrives • ToF is translated into distance Distance Value = Photon travel time/2 x by speed of light

  Performance, Principles, Challenges, Time, Flight, Towards, Performance and, Flight principles