目标检测 Object Detection
本文收集目标检测相关论文,会在之后持续更新。
Leaderboard
Object Detector
Detector | Backbone | VOC | COCO | Paper |
---|
Pedestrain Detector
Detector | Backbone | Caltech(MR-2) | Caltech(MR-4) | Paper |
---|
Paper
Object Detection
RoI
RepPoints: Point Set Representation for Object Detection
CornerNet-Lite: Efficient Keypoint Based Object Detection
Objects as Points
DuBox: No-Prior Box Objection Detection via Residual Dual Scale Detectors
- arXiv: http://arxiv.org/abs/1904.06883
- note: Note-DuBox: No-Prior Box Objection Detection via Residual Dual Scale Detectors
FoveaBox: Beyond Anchor-based Object Detector
High-level Semantic Feature Detection:A New Perspective for Pedestrian Detection
- arXiv: https://arxiv.org/abs/1904.02948
- github: https://github.com/liuwei16/CSP
- pub: CVPR 2019
FCOS: Fully Convolutional One-Stage Object Detection
Feature Selective Anchor-Free Module for Single-Shot Object Detection
Bottom-up Object Detection by Grouping Extreme and Center Points
Region Proposal by Guided Anchoring
- arXiv: http://arxiv.org/abs/1901.03278
- pub: CVPR 2019
CornerNet: Detecting Objects as Paired Keypoints
DeNet Scalable Real-Time Object Detection With Directed Sparse Sampling
- arxiv: https://arxiv.org/abs/1703.10295
- pub: ICCV 2017
- [note](2017 - Tychsen-Smith, Petersson - DeNet Scalable Real-Time Object Detection With Directed Sparse Sampling.md)论文笔记《DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling》
Feature
Libra R-CNN: Towards Balanced Learning for Object Detection
- paper: https://arxiv.org/abs/1904.02701
- code: https://github.com/open-mmlab/mmdetection
- pub: CVPR 2018
$\star$ Multi-scale Location-aware Kernel Representation for Object Detection
- arxiv: https://arxiv.org/abs/1804.00428
- pub: CVPR 2018
- github: https://github.com/Hwang64/MLKP
Post process
Softer-NMS: Rethinking Bounding Box Regression for Accurate Object Detection
Soft-NMS – Improving Object Detection With One Line of Code
- arxiv: https://arxiv.org/abs/1704.04503
- pub: ICCV 2017
- github: https://github.com/bharatsingh430/soft-nms
- [note](2017 - Bodla et al. - Soft-NMS – Improving Object Detection With One Line of Code.md) 论文笔记《Soft-NMS – Improving Object Detection With One Line of Code》
Pedestrian Detection
PCN: Part and Context Information for Pedestrian Detection with CNNs
- arxiv: https://arxiv.org/abs/1804.04483
- pub: BMVC 2017
Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond
- arxiv: https://arxiv.org/abs/1804.02047
- github: https://github.com/yueruchen/Pedestrian-Synthesis-GAN
Illumination-aware Faster R-CNN for Robust Multispectral Pedestrian Detection
Repulsion Loss: Detecting Pedestrians in a Crowd
- arxiv: https://arxiv.org/abs/1711.07752
- pub: CVPR 2018
Illuminating Pedestrians via Simultaneous Detection & Segmentation
- arxiv: https://arxiv.org/abs/1706.08564
- pub: ICCV 2017
- paper
What Can Help Pedestrian Detection?
- arxiv: https://arxiv.org/abs/1705.02757
- pub: CVPR 2017
Expecting the Unexpected: Training Detectors for Unusual Pedestrians with Adversarial Imposters
- arxiv: https://arxiv.org/abs/1703.06283
- pub: CVPR 2017
CityPersons: A Diverse Dataset for Pedestrian Detection
- arxiv: https://arxiv.org/abs/1702.05693
- [note](2017 - Zhang, Benenson, Schiele - CityPersons A Diverse Dataset for Pedestrian Detection.md)论文笔记《CityPersons: A Diverse Dataset for Pedestrian Detection》
Deep Multi-Camera People Detection
- arxiv: https://arxiv.org/abs/1702.04593
- pub: International Conference on Machine Learning and Applications
Multispectral Deep Neural Networks for Pedestrian Detection
- arxiv: https://arxiv.org/abs/1611.02644
- pub: BMVC 2016 oral
Fused DNN A Deep Neural Network Fusion Approach to Fast and Robust Pedestrian Detection
- arxiv: https://arxiv.org/abs/1610.03466
- pub: WACV 2017
- [note](2017 - Du et al. - Fused DNN A Deep Neural Network Fusion Approach to Fast and Robust Pedestrian Detection.md)
Is Faster R-CNN Doing Well for Pedestrian Detection
- arxiv: https://arxiv.org/abs/1607.07032
- pub: ECCV 2016
- [note](2016 - Zhang et al. - Is Faster R-CNN Doing Well for Pedestrian Detection.md)论文笔记《Is Faster R-CNN Doing Well for Pedestrian Detection?》
Video Object Detection
Learning Correspondence from the Cycle-Consistency of Time
- pub: CVPR 2019 (oral)
- github: https://github.com/xiaolonw/TimeCycle
Detect-and-Track: Efficient Pose Estimation in Videos
- arxiv: https://arxiv.org/abs/1712.09184
- pub: CVPR 2018
- github: https://github.com/facebookresearch/DetectAndTrack
- intro: 1st ICCV 2017 PoseTrack
Flow-Guided Feature Aggregation for Video Object Detection
- arxiv: https://arxiv.org/abs/1703.10025
- pub: ICCV 2017
- github: https://github.com/msracver/Flow-Guided-Feature-Aggregation
- [note](2017 - Zhu et al. - Flow-Guided Feature Aggregation for Video Object Detection.md)论文笔记《Deep Feature Flow for Video Recognition》
Deep Feature Flow for Video Recognition
- arxiv: https://arxiv.org/abs/1611.07715
- pub: CVPR 2017
- [note](2017 - Zhu et al. - Deep Feature Flow for Video Recognition.md)论文笔记《Deep Feature Flow for Video Recognition》
Segmentation
YOLACT: Real-time Instance Segmentation
- arxiv: https://arxiv.org/abs/1904.02689
- github: https://github.com/dbolya/yolact
Rethinking Atrous Convolution for Semantic Image Segmentation
- arxiv: https://arxiv.org/abs/1706.05587
- [note](2017 - Chen et al. - Rethinking Atrous Convolution for Semantic Image Segmentation.md)论文笔记《Rethinking Atrous Convolution for Semantic Image Segmentation》