计算机视觉各个方向论文速览

Last updated: 2019/08/30

Update log

• 2019/08/30 * -

Table of Contents

• 目标检测

Top Papers of Object Detection

2019 CVPR of Object Detection

• Feature Selective Anchor-Free Module for Single-Shot Object Detection

• Bottom-up Object Detection by Grouping Extreme and Center Points [pytorch]

• C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection [ torch]

• MaxpoolNMS: Getting Rid of NMS Bottlenecks in Two-Stage Object Detectors

• You reap what you sow: Generating High Precision Object Proposals for Weakly-supervised Object Detection

• Object detection with location-aware deformable convolution and backward attention filtering

• ScratchDet: Training Single-Shot Object Detectors from Scratch

• Bounding Box Regression with Uncertainty for Accurate Object Detection [caffe2]

• Activity Driven Weakly Supervised Object Detection

• Towards Accurate One-Stage Object Detection with AP-Loss

• Strong-Weak Distribution Alignment for Adaptive Object Detection [pytorch]

• NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection

• Adaptive NMS: Refining Pedestrian Detection in a Crowd

• Point in, Box out: Beyond Counting Persons in Crowds

• Locating Objects Without Bounding Boxes

• Sampling Techniques for Large-Scale Object Detection from Sparsely Annotated Objects

• Towards Universal Object Detection by Domain Attention

• Exploring the Bounds of the Utility of Context for Object Detection

• What Object Should I Use? Task Driven Object Detection

• Dissimilarity Coefficient based Weakly Supervised Object Detection

• Adapting Object Detectors via Selective Cross-Domain Alignment

• Fully Quantized Network for Object Detection

• Distilling Object Detectors with Fine-grained Feature Imitation

• Multi-task Self-Supervised Object Detection via Recycling of Bounding Box Annotations

• Reasoning-RCNN: Unifying Adaptive Global Reasoning into Large-scale Object Detection

• Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression

• Automatic adaptation of object detectors to new domains using self-training

• Libra R-CNN: Balanced Learning for Object Detection

• Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation

• Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors

• Spatial-aware Graph Relation Network for Large-scale Object Detection

• Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection

2019 ICLR of Object Detection

• CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the Wild

• Feature Intertwiner for Object Detection

2019 AAAI of Object Detection

• M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network [pytorch]

• Object Detection based on Region Decomposition and Assembly

2018 CVPR of Object Detection

• [DA Faster R-CNN]Domain Adaptive Faster R-CNN for Object Detection in the Wild [caffe]

• [SNIP]An Analysis of Scale Invariance in Object Detection – SNIP

• [Relation-Network]Relation Networks for Object Detection [mxnet]

• [Cascade R-CNN]Cascade R-CNN: Delving into High Quality Object Detection [caffe]

• [SIN]Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships [tensorflow]

• [STDN]Scale-Transferrable Object Detection

• [RefineDet]Single-Shot Refinement Neural Network for Object Detection [caffe]

• [MegDet]MegDet: A Large Mini-Batch Object Detector

• Finding Tiny Faces in the Wild with Generative Adversarial Network

• [MLKP]Multi-scale Location-aware Kernel Representation for Object Detection [caffe]

• Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation [chainer]

• [Fitness NMS]Improving Object Localization with Fitness NMS and Bounded IoU Loss

2018 ECCV of Object Detection

• [RFBNet]Receptive Field Block Net for Accurate and Fast Object Detection [pytorch]

• Zero-Annotation Object Detection with Web Knowledge Transfer

• [CornerNet]CornerNet: Detecting Objects as Paired Keypoints [pytorch]

• [PFPNet]Parallel Feature Pyramid Network for Object Detection

2018 NIPS of Object Detection

• [Pelee]Pelee: A Real-Time Object Detection System on Mobile Devices [caffe]

• [HKRM]Hybrid Knowledge Routed Modules for Large-scale Object Detection

• [MetaAnchor]MetaAnchor: Learning to Detect Objects with Customized Anchors

• [SNIPER]SNIPER: Efficient Multi-Scale Training

2017 CVPR of Object Detection

• [DSSD]DSSD : Deconvolutional Single Shot Detector [caffe]

• [TDM]Beyond Skip Connections: Top-Down Modulation for Object Detection

• [FPN]Feature Pyramid Networks for Object Detection

• [YOLO v2]YOLO9000: Better, Faster, Stronger [c]

• [RON]RON: Reverse Connection with Objectness Prior Networks for Object Detection [caffe]

2017 ICCV of Object Detection

• [DeNet]DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling [theano]

• [CoupleNet]CoupleNet: Coupling Global Structure with Local Parts for Object Detection [caffe]

• [RetinaNet]Focal Loss for Dense Object Detection [keras]

• [Mask R-CNN]Mask R-CNN [caffe2]

• [RSA]Recurrent Scale Approximation for Object Detection in CNN | [caffe]

• [DCN]Deformable Convolutional Networks [mxnet]

• [DSOD]DSOD: Learning Deeply Supervised Object Detectors from Scratch [caffe]

• [SMN]Spatial Memory for Context Reasoning in Object Detection

• [Light-Head R-CNN]Light-Head R-CNN: In Defense of Two-Stage Object Detector [tensorflow]

• [Soft-NMS]Improving Object Detection With One Line of Code [caffe]

2016 CVPR of Object Detection

• [YOLO v1]You Only Look Once: Unified, Real-Time Object Detection [c]

• [G-CNN]G-CNN: an Iterative Grid Based Object Detector

• [AZNet]Adaptive Object Detection Using Adjacency and Zoom Prediction

• [ION]Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks

• [HyperNet]HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection

• [OHEM]Training Region-based Object Detectors with Online Hard Example Mining [caffe]

• [CRAPF]CRAFT Objects from Images [caffe]

2016 ECCV of Object Detection

• [SSD]SSD: Single Shot MultiBox Detector [caffe]

• [GBDNet]Crafting GBD-Net for Object Detection [caffe]

• [CPF]Contextual Priming and Feedback for Faster R-CNN

• [MS-CNN]A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection [caffe]

2016 NIP and PAMI of Object Detection

• [R-FCN] [NIPS' 16]R-FCN: Object Detection via Region-based Fully Convolutional Networks [caffe]

• [PVANET]****[NIPSW' 16]PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection [caffe]

• [DeepID-Net]****[PAMI' 16]DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection

• [NoC]****[TPAMI' 16]Object Detection Networks on Convolutional Feature Maps

2015 CVPR and NIPS of Object Detection

• Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction [matlab]

• [Faster R-CNN, RPN]****[NIPS' 15]Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks [caffe]

2015 ICCV of Object Detection

• [MR-CNN]Object detection via a multi-region & semantic segmentation-aware CNN model [caffe]

• [DeepBox]DeepBox: Learning Objectness with Convolutional Networks [caffe]

• [AttentionNet]AttentionNet: Aggregating Weak Directions for Accurate Object Detection

• [Fast R-CNN]Fast R-CNN [caffe]

• [DeepProposal]DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers [matconvnet]

2014 CVPR & ICLR & ECCV of Object Detection

• [R-CNN]Rich feature hierarchies for accurate object detection and semantic segmentation [caffe]

• [OverFeat]****[ICLR' 14]OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks [torch]

• [MultiBox]Scalable Object Detection using Deep Neural Networks

• [SPP-Net]****[ECCV' 14]Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition [caffe]

Image Classification

2019-07-07

• Multi-Instance Multi-Scale CNN for Medical Image Classification

Semantic Segmentation

2019-07-08

• Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation

• FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation [paper][code]

Object Detection

2019-07-09

• Multi-Cue Vehicle Detection for Semantic Video Compression In Georegistered Aerial Videos