Object Detection(目标检测神文)(二)

「爱情、让人受尽委屈。」 2022-03-01 08:28 536阅读 0赞

### 文章目录 ###

*   *   *  \[CVPR2019\] Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression
     *  anchor-free
     *   *  \[CVPR2019\] Region Proposal by Guided Anchoring
         *  \[CVPR2019\] Feature Selective Anchor-Free Module for Single-Shot Object Detection
         *  \[CVPR2019\]CenterNet: Keypoint Triplets for Object Detection
         *  \[CVPR2019\]Objects as Points
         *  \[CVPR2019\]CornerNet-Lite: Efficient Keypoint Based Object Detection
         *  \[CVPR2019\]FoveaBox: Beyond Anchor-based Object Detector
         *  \[2019\]DuBox: No-Prior Box Objection Detection via Residual Dual Scale Detectors
     *  YOLO
     *   *  \[2019\]Spiking-YOLO: Spiking Neural Network for Real-time Object Detection
         *  \[CVPR2019\]Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving
 *  
 *   *   *  \[AAAI2019\]Gradient Harmonized Single-stage Detector
         *  \[2019\]Augmentation for small object detection
         *  \[2019\]SimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition
         *  \[2019\]BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectors
         *  \[2019\]DetNAS: Neural Architecture Search on Object Detection
         *  \[2019\]ThunderNet: Towards Real-time Generic Object Detection
         *  \[2019\]Feature Intertwiner for Object Detection
         *  \[CVPR2019\]Few-shot Adaptive Faster R-CNN
         *  \[2019\]Improving Object Detection with Inverted Attention
         *  \[2019\]FCOS: Fully Convolutional One-Stage Object Detection
         *  \[CVPR2019\]Libra R-CNN: Towards Balanced Learning for Object Detection
         *  \[2019\]Complexer-YOLO: Real-Time 3D Object Detection and Tracking on Semantic Point Clouds
         *  \[CVPR2019\]What Object Should I Use? - Task Driven Object Detection
         *  \[CVPR2019\]Towards Universal Object Detection by Domain Attention
         *  \[2019\]Prime Sample Attention in Object Detection
         *  \[2019\]BAOD: Budget-Aware Object Detection
         *  \[2019\]An Analysis of Pre-Training on Object Detection
         *  \[2019\]Rethinking Classification and Localization in R-CNN
         *  \[CVPR2019\]NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
         *  \[2019\]Automated Focal Loss for Image based Object Detection
         *  \[2019\]LFFD: A Light and Fast Face Detector for Edge Devices
         *  \[CVPR2019\]Exploring Object Relation in Mean Teacher for Cross-Domain Detection
         *  \[2019\]HAR-Net: Joint Learning of Hybrid Attention for Single-stage Object Detection
         *  \[2019\]An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection
         *  \[2019\]RepPoints: Point Set Representation for Object Detection
         *  \[2019\]Object Detection in 20 Years: A Survey
         *  \[AAAI2019\]SCNN: A General Distribution based Statistical Convolutional Neural Network with Application to Video Object Detection
         *  \[2019\]Looking Fast and Slow: Memory-Guided Mobile Video Object Detection
         *  \[2019\]Progressive Sparse Local Attention for Video object detection
         *  \[2019\]Exploring the Semantics for Visual Relationship Detection
         *  \[2019\]PyramidBox++: High Performance Detector for Finding Tiny Face
         *  \[ICPR2018\]MSFD:Multi-Scale Receptive Field Face Detector
         *  \[CVPR2018\]Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors
         *  \[ECCV2018\]Bi-box Regression for Pedestrian Detection and Occlusion Estimation
         *  \[2019\]SSA-CNN: Semantic Self-Attention CNN for Pedestrian Detection
         *  \[2019\]Box-level Segmentation Supervised Deep Neural Networks for Accurate and Real-time Multispectral Pedestrian Detection
         *  \[2019\]GFD-SSD: Gated Fusion Double SSD for Multispectral Pedestrian Detection
         *  \[CVPR2019\]High-level Semantic Feature Detection:A New Perspective for Pedestrian Detection
     *  Pedestrian Detection in a Crowd
     *   *  \[CVPR2018\]Repulsion Loss: Detecting Pedestrians in a Crowd
         *  \[ECCV2018\]Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd
         *  \[CVPR2019\]Adaptive NMS: Refining Pedestrian Detection in a Crowd
         *  \[2019\]Unsupervised Domain Adaptation for Multispectral Pedestrian Detection

### \[CVPR2019\] Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression ###

*  arxiv: [https://arxiv.org/abs/1902.09630][https_arxiv.org_abs_1902.09630]

## anchor-free ##

无锚框最近的热点，有机会研究下。

### \[CVPR2019\] Region Proposal by Guided Anchoring ###

*  intro: CUHK - SenseTime Joint Lab & Amazon Rekognition & Nanyang Technological University
 *  arxiv: [https://arxiv.org/abs/1901.03278][https_arxiv.org_abs_1901.03278]

### \[CVPR2019\] Feature Selective Anchor-Free Module for Single-Shot Object Detection ###

*  intro: FSAF for Single-Shot Object Detection
 *  arxiv: [https://arxiv.org/abs/1903.00621][https_arxiv.org_abs_1903.00621]

### \[CVPR2019\]CenterNet: Keypoint Triplets for Object Detection ###

*  intro: CornerNet改进
 *  arxiv: [https://arxiv.org/abs/1904.08189][https_arxiv.org_abs_1904.08189]
 *  github: [https://github.com/Duankaiwen/CenterNet][https_github.com_Duankaiwen_CenterNet]

### \[CVPR2019\]Objects as Points ###

*  intro: CornerNet改进
 *  arxiv: [https://arxiv.org/pdf/1904.07850.pdf][https_arxiv.org_pdf_1904.07850.pdf]
 *  github: [https://github.com/xingyizhou/CenterNet][https_github.com_xingyizhou_CenterNet]

### \[CVPR2019\]CornerNet-Lite: Efficient Keypoint Based Object Detection ###

*  intro: CornerNet改进，mAP34.4%-34ms
 *  arxiv: [https://arxiv.org/abs/1904.08900][https_arxiv.org_abs_1904.08900]
 *  github: [https://github.com/princeton-vl/CornerNet-Lite][https_github.com_princeton-vl_CornerNet-Lite]

### \[CVPR2019\]FoveaBox: Beyond Anchor-based Object Detector ###

*  intro:
 *  arxiv: [https://arxiv.org/abs/1904.03797][https_arxiv.org_abs_1904.03797]
 *  github:

### \[2019\]DuBox: No-Prior Box Objection Detection via Residual Dual Scale Detectors ###

*  intro: Baidu Inc.
 *  arxiv: [https://arxiv.org/abs/1904.06883][https_arxiv.org_abs_1904.06883]

## YOLO ##

### \[2019\]Spiking-YOLO: Spiking Neural Network for Real-time Object Detection ###

*  arxiv: [https://arxiv.org/abs/1903.06530][https_arxiv.org_abs_1903.06530]

### \[CVPR2019\]Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving ###

*  arxiv: [https://arxiv.org/abs/1904.04620][https_arxiv.org_abs_1904.04620]

#  #

### \[AAAI2019\]Gradient Harmonized Single-stage Detector ###

*  intro: AAAI 2019 Oral
 *  arxiv: [https://arxiv.org/abs/1811.05181][https_arxiv.org_abs_1811.05181]
 *  gihtub(official): [https://github.com/libuyu/GHM\_Detection][https_github.com_libuyu_GHM_Detection]

### \[2019\]Augmentation for small object detection ###

*  arxiv: [https://arxiv.org/abs/1902.07296][https_arxiv.org_abs_1902.07296]

### \[2019\]SimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition ###

*  intro: TuSimple
 *  arxiv: [https://arxiv.org/abs/1903.05831][https_arxiv.org_abs_1903.05831]
 *  github: [https://github.com/tusimple/simpledet][https_github.com_tusimple_simpledet]

### \[2019\]BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectors ###

*  intro: University of Toronto
 *  arxiv: [https://arxiv.org/abs/1903.03838][https_arxiv.org_abs_1903.03838]

### \[2019\]DetNAS: Neural Architecture Search on Object Detection ###

*  intro: Chinese Academy of Sciences & Megvii Inc
 *  arxiv: [https://arxiv.org/abs/1903.10979][https_arxiv.org_abs_1903.10979]

### \[2019\]ThunderNet: Towards Real-time Generic Object Detection ###

[https://arxiv.org/abs/1903.11752][https_arxiv.org_abs_1903.11752]

### \[2019\]Feature Intertwiner for Object Detection ###

*  intro: ICLR 2019
 *  intro: CUHK & SenseTime & The University of Sydney
 *  arxiv: [https://arxiv.org/abs/1903.11851][https_arxiv.org_abs_1903.11851]

### \[CVPR2019\]Few-shot Adaptive Faster R-CNN ###

*  intro: CVPR 2019
 *  arxiv: [https://arxiv.org/abs/1903.09372][https_arxiv.org_abs_1903.09372]

### \[2019\]Improving Object Detection with Inverted Attention ###

*  arxiv: [https://arxiv.org/abs/1903.12255][https_arxiv.org_abs_1903.12255]

### \[2019\]FCOS: Fully Convolutional One-Stage Object Detection ###

*  arxiv: [https://arxiv.org/abs/1904.01355][https_arxiv.org_abs_1904.01355]

### \[CVPR2019\]Libra R-CNN: Towards Balanced Learning for Object Detection ###

*  intro: CVPR 2019
 *  arxiv: [https://arxiv.org/abs/1904.02701][https_arxiv.org_abs_1904.02701]

### \[2019\]Complexer-YOLO: Real-Time 3D Object Detection and Tracking on Semantic Point Clouds ###

*  arxiv: [https://arxiv.org/abs/1904.07537][https_arxiv.org_abs_1904.07537]
 *

### \[CVPR2019\]What Object Should I Use? - Task Driven Object Detection ###

intro: CVPR 2019  
arxiv: [https://arxiv.org/abs/1904.03000][https_arxiv.org_abs_1904.03000]

FoveaBox: Beyond Anchor-based Object Detector  
intro: Tsinghua University & BNRist & ByteDance AI Lab & University of Pennsylvania  
arxiv: [https://arxiv.org/abs/1904.03797][https_arxiv.org_abs_1904.03797]

### \[CVPR2019\]Towards Universal Object Detection by Domain Attention ###

*  intro: CVPR 2019
 *  arxiv: [https://arxiv.org/abs/1904.04402][https_arxiv.org_abs_1904.04402]

### \[2019\]Prime Sample Attention in Object Detection ###

*  arxiv: [https://arxiv.org/abs/1904.04821][https_arxiv.org_abs_1904.04821]

### \[2019\]BAOD: Budget-Aware Object Detection ###

*  arxiv: [https://arxiv.org/abs/1904.05443][https_arxiv.org_abs_1904.05443]

### \[2019\]An Analysis of Pre-Training on Object Detection ###

*  intro: University of Maryland
 *  arxiv: [https://arxiv.org/abs/1904.05871][https_arxiv.org_abs_1904.05871]

### \[2019\]Rethinking Classification and Localization in R-CNN ###

*  intro: Northeastern University & Microsoft
 *  arxiv: [https://arxiv.org/abs/1904.06493][https_arxiv.org_abs_1904.06493]

### \[CVPR2019\]NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection ###

*  intro: CVPR 2019, Google Brain
 *  arxiv: [https://arxiv.org/abs/1904.07392][https_arxiv.org_abs_1904.07392]

### \[2019\]Automated Focal Loss for Image based Object Detection ###

*  arxiv: [https://arxiv.org/abs/1904.09048][https_arxiv.org_abs_1904.09048]

### \[2019\]LFFD: A Light and Fast Face Detector for Edge Devices ###

*  arxiv: [https://arxiv.org/abs/1904.10633][https_arxiv.org_abs_1904.10633]

### \[CVPR2019\]Exploring Object Relation in Mean Teacher for Cross-Domain Detection ###

*  intro: CVPR 2019
 *  arxiv: [https://arxiv.org/abs/1904.11245][https_arxiv.org_abs_1904.11245]

### \[2019\]HAR-Net: Joint Learning of Hybrid Attention for Single-stage Object Detection ###

*  arxiv: [https://arxiv.org/abs/1904.11141][https_arxiv.org_abs_1904.11141]

### \[2019\]An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection ###

intro: CVPR 2019 CEFRL Workshop  
arxiv: [https://arxiv.org/abs/1904.09730][https_arxiv.org_abs_1904.09730]

### \[2019\]RepPoints: Point Set Representation for Object Detection ###

*  intro: Peking University & Tsinghua University & Microsoft Research Asia
 *  arxiv: [https://arxiv.org/abs/1904.11490][https_arxiv.org_abs_1904.11490]

### \[2019\]Object Detection in 20 Years: A Survey ###

*  arxiv: [https://arxiv.org/abs/1905.05055][https_arxiv.org_abs_1905.05055]

### \[AAAI2019\]SCNN: A General Distribution based Statistical Convolutional Neural Network with Application to Video Object Detection ###

*  intro: AAAI 2019
 *  arxiv: [https://arxiv.org/abs/1903.07663][https_arxiv.org_abs_1903.07663]

### \[2019\]Looking Fast and Slow: Memory-Guided Mobile Video Object Detection ###

*  intro: Cornell University & Google AI
 *  arxiv: [https://arxiv.org/abs/1903.10172][https_arxiv.org_abs_1903.10172]

### \[2019\]Progressive Sparse Local Attention for Video object detection ###

*  intro: NLPR,CASIA & Horizon Robotics
 *  arxiv: [https://arxiv.org/abs/1903.09126][https_arxiv.org_abs_1903.09126]

### \[2019\]Exploring the Semantics for Visual Relationship Detection ###

*  arxiv: [https://arxiv.org/abs/1904.02104][https_arxiv.org_abs_1904.02104]

### \[2019\]PyramidBox++: High Performance Detector for Finding Tiny Face ###

*  intro: Chinese Academy of Sciences & Baidu, Inc.
 *  arxiv: [https://arxiv.org/abs/1904.00386][https_arxiv.org_abs_1904.00386]

### \[ICPR2018\]MSFD:Multi-Scale Receptive Field Face Detector ###

*  intro: ICPR 2018
 *  arxiv: [https://arxiv.org/abs/1903.04147][https_arxiv.org_abs_1903.04147]

### \[CVPR2018\]Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors ###

*  intro: CVPR 2018
 *  paper: [http://openaccess.thecvf.com/content\_cvpr\_2018/papers/Noh\_Improving\_Occlusion\_and\_CVPR\_2018\_paper.pdf][http_openaccess.thecvf.com_content_cvpr_2018_papers_Noh_Improving_Occlusion_and_CVPR_2018_paper.pdf]

### \[ECCV2018\]Bi-box Regression for Pedestrian Detection and Occlusion Estimation ###

*  intro: ECCV 2018
 *  paper: [http://openaccess.thecvf.com/content\_ECCV\_2018/papers/CHUNLUAN\_ZHOU\_Bi-box\_Regression\_for\_ECCV\_2018\_paper.pdf][http_openaccess.thecvf.com_content_ECCV_2018_papers_CHUNLUAN_ZHOU_Bi-box_Regression_for_ECCV_2018_paper.pdf]
 *  github(Pytorch): [https://github.com/rainofmine/Bi-box\_Regression][https_github.com_rainofmine_Bi-box_Regression]

### \[2019\]SSA-CNN: Semantic Self-Attention CNN for Pedestrian Detection ###

*  arxiv: [https://arxiv.org/abs/1902.09080][https_arxiv.org_abs_1902.09080]

### \[2019\]Box-level Segmentation Supervised Deep Neural Networks for Accurate and Real-time Multispectral Pedestrian Detection ###

*  arxiv: [https://arxiv.org/abs/1902.05291][https_arxiv.org_abs_1902.05291]

### \[2019\]GFD-SSD: Gated Fusion Double SSD for Multispectral Pedestrian Detection ###

*  arxiv: [https://arxiv.org/abs/1903.06999][https_arxiv.org_abs_1903.06999]
 *

### \[CVPR2019\]High-level Semantic Feature Detection:A New Perspective for Pedestrian Detection ###

*  intro: CVPR 2019
 *  intro: National University of Defense Technology & Chinese Academy of Sciences & Inception Institute of Artificial Intelligence (IIAI) & Horizon Robotics Inc.
 *  arxiv: [https://arxiv.org/abs/1904.02948][https_arxiv.org_abs_1904.02948]
 *  github(official, Keras): [https://github.com/liuwei16/CSP][https_github.com_liuwei16_CSP]

## Pedestrian Detection in a Crowd ##

### \[CVPR2018\]Repulsion Loss: Detecting Pedestrians in a Crowd ###

*  intro: CVPR 2018
 *  arxiv: [https://arxiv.org/abs/1711.07752][https_arxiv.org_abs_1711.07752]

### \[ECCV2018\]Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd ###

*  intro: ECCV 2018
 *  arxiv: [https://arxiv.org/abs/1807.08407][https_arxiv.org_abs_1807.08407]

### \[CVPR2019\]Adaptive NMS: Refining Pedestrian Detection in a Crowd ###

*  intro: CVPR 2019 oral
 *  arxiv: [https://arxiv.org/abs/1904.03629][https_arxiv.org_abs_1904.03629]

### \[2019\]Unsupervised Domain Adaptation for Multispectral Pedestrian Detection ###

*  arxiv: [https://arxiv.org/abs/1904.03692][https_arxiv.org_abs_1904.03692]

[https_arxiv.org_abs_1902.09630]: https://arxiv.org/abs/1902.09630
[https_arxiv.org_abs_1901.03278]: https://arxiv.org/abs/1901.03278
[https_arxiv.org_abs_1903.00621]: https://arxiv.org/abs/1903.00621
[https_arxiv.org_abs_1904.08189]: https://arxiv.org/abs/1904.08189
[https_github.com_Duankaiwen_CenterNet]: https://github.com/Duankaiwen/CenterNet
[https_arxiv.org_pdf_1904.07850.pdf]: https://arxiv.org/pdf/1904.07850.pdf
[https_github.com_xingyizhou_CenterNet]: https://github.com/xingyizhou/CenterNet
[https_arxiv.org_abs_1904.08900]: https://arxiv.org/abs/1904.08900
[https_github.com_princeton-vl_CornerNet-Lite]: https://github.com/princeton-vl/CornerNet-Lite
[https_arxiv.org_abs_1904.03797]: https://arxiv.org/abs/1904.03797
[https_arxiv.org_abs_1904.06883]: https://arxiv.org/abs/1904.06883
[https_arxiv.org_abs_1903.06530]: https://arxiv.org/abs/1903.06530
[https_arxiv.org_abs_1904.04620]: https://arxiv.org/abs/1904.04620
[https_arxiv.org_abs_1811.05181]: https://arxiv.org/abs/1811.05181
[https_github.com_libuyu_GHM_Detection]: https://github.com/libuyu/GHM_Detection
[https_arxiv.org_abs_1902.07296]: https://arxiv.org/abs/1902.07296
[https_arxiv.org_abs_1903.05831]: https://arxiv.org/abs/1903.05831
[https_github.com_tusimple_simpledet]: https://github.com/tusimple/simpledet
[https_arxiv.org_abs_1903.03838]: https://arxiv.org/abs/1903.03838
[https_arxiv.org_abs_1903.10979]: https://arxiv.org/abs/1903.10979
[https_arxiv.org_abs_1903.11752]: https://arxiv.org/abs/1903.11752
[https_arxiv.org_abs_1903.11851]: https://arxiv.org/abs/1903.11851
[https_arxiv.org_abs_1903.09372]: https://arxiv.org/abs/1903.09372
[https_arxiv.org_abs_1903.12255]: https://arxiv.org/abs/1903.12255
[https_arxiv.org_abs_1904.01355]: https://arxiv.org/abs/1904.01355
[https_arxiv.org_abs_1904.02701]: https://arxiv.org/abs/1904.02701
[https_arxiv.org_abs_1904.07537]: https://arxiv.org/abs/1904.07537
[https_arxiv.org_abs_1904.03000]: https://arxiv.org/abs/1904.03000
[https_arxiv.org_abs_1904.04402]: https://arxiv.org/abs/1904.04402
[https_arxiv.org_abs_1904.04821]: https://arxiv.org/abs/1904.04821
[https_arxiv.org_abs_1904.05443]: https://arxiv.org/abs/1904.05443
[https_arxiv.org_abs_1904.05871]: https://arxiv.org/abs/1904.05871
[https_arxiv.org_abs_1904.06493]: https://arxiv.org/abs/1904.06493
[https_arxiv.org_abs_1904.07392]: https://arxiv.org/abs/1904.07392
[https_arxiv.org_abs_1904.09048]: https://arxiv.org/abs/1904.09048
[https_arxiv.org_abs_1904.10633]: https://arxiv.org/abs/1904.10633
[https_arxiv.org_abs_1904.11245]: https://arxiv.org/abs/1904.11245
[https_arxiv.org_abs_1904.11141]: https://arxiv.org/abs/1904.11141
[https_arxiv.org_abs_1904.09730]: https://arxiv.org/abs/1904.09730
[https_arxiv.org_abs_1904.11490]: https://arxiv.org/abs/1904.11490
[https_arxiv.org_abs_1905.05055]: https://arxiv.org/abs/1905.05055
[https_arxiv.org_abs_1903.07663]: https://arxiv.org/abs/1903.07663
[https_arxiv.org_abs_1903.10172]: https://arxiv.org/abs/1903.10172
[https_arxiv.org_abs_1903.09126]: https://arxiv.org/abs/1903.09126
[https_arxiv.org_abs_1904.02104]: https://arxiv.org/abs/1904.02104
[https_arxiv.org_abs_1904.00386]: https://arxiv.org/abs/1904.00386
[https_arxiv.org_abs_1903.04147]: https://arxiv.org/abs/1903.04147
[http_openaccess.thecvf.com_content_cvpr_2018_papers_Noh_Improving_Occlusion_and_CVPR_2018_paper.pdf]: http://openaccess.thecvf.com/content_cvpr_2018/papers/Noh_Improving_Occlusion_and_CVPR_2018_paper.pdf
[http_openaccess.thecvf.com_content_ECCV_2018_papers_CHUNLUAN_ZHOU_Bi-box_Regression_for_ECCV_2018_paper.pdf]: http://openaccess.thecvf.com/content_ECCV_2018/papers/CHUNLUAN_ZHOU_Bi-box_Regression_for_ECCV_2018_paper.pdf
[https_github.com_rainofmine_Bi-box_Regression]: https://github.com/rainofmine/Bi-box_Regression
[https_arxiv.org_abs_1902.09080]: https://arxiv.org/abs/1902.09080
[https_arxiv.org_abs_1902.05291]: https://arxiv.org/abs/1902.05291
[https_arxiv.org_abs_1903.06999]: https://arxiv.org/abs/1903.06999
[https_arxiv.org_abs_1904.02948]: https://arxiv.org/abs/1904.02948
[https_github.com_liuwei16_CSP]: https://github.com/liuwei16/CSP
[https_arxiv.org_abs_1711.07752]: https://arxiv.org/abs/1711.07752
[https_arxiv.org_abs_1807.08407]: https://arxiv.org/abs/1807.08407
[https_arxiv.org_abs_1904.03629]: https://arxiv.org/abs/1904.03629
[https_arxiv.org_abs_1904.03692]: https://arxiv.org/abs/1904.03692