【论文汇总】2D目标检测文章汇总,持续更新

记录自己比较感兴趣的2D目标检测文章

1.模型架构相关

DatePub.TitleCode
2022ECCVObjectBox: From Centers to Boxes for Anchor-Free Object Detectionhttps://github.com/mohsenzand/objectbox
2021MMDisentangle Your Dense Object Detectorhttps://github.com/zehuichen123/DDOD
2021CVPRVarifocalNet: An IoU-aware Dense Object Detectorhttps://github.com/hyz-xmaster/VarifocalNet
2021CVPRSparse R-CNN: End-to-End Object Detection with Learnable Proposalshttps://github.com/PeizeSun/SparseR-CNN
2020ECCVDynamic R-CNN: Towards High Quality Object Detection via Dynamic Traininghttps://github.com/hkzhang95/DynamicRCNN
2020ECCVSide-Aware Boundary Localization for More Precise Object Detectionhttps://github.com/open-mmlab/mmdetection
2020CVPRCentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detectionhttps://github.com/KiveeDong/CentripetalNet
2020CVPRNAS-FCOS: Fast Neural Architecture Search for Object Detectionhttps://github.com/open-mmlab/mmdetection
2020TIPFoveaBox: Beyond Anchor-based Object Detectorhttps://github.com/taokong/FoveaBox
2020NIPSRepPoints V2: Verification Meets Regression for Object Detectionhttps://github.com/Scalsol/RepPointsV2
2019ICCVRepPoints: Point Set Representation for Object Detectionhttps://github.com/microsoft/RepPoints
2019NIPSCascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolutionhttps://github.com/thangvubk/Cascade-RPN
2019ICCVFCOS: Fully Convolutional One-Stage Object Detectionhttps://github.com/tianzhi0549/FCOS
2019ICCVScale-Aware Trident Networks for Object Detectionhttps://github.com/open-mmlab/mmdetection
2019CVPRLibra R-CNN: Towards Balanced Learning for Object Detectionhttps://github.com/open-mmlab/mmdetection
2019CVPRObjects as Pointshttps://github.com/xingyizhou/CenterNet
2019CVPRRegion Proposal by Guided Anchoringhttps://github.com/open-mmlab/mmdetection
2019CVPRGrid R-CNNhttps://github.com/open-mmlab/mmdetection
2018ECCVCornerNet: Detecting Objects as Paired Keypointshttps://github.com/princeton-vl/CornerNet
2018CVPRCascade R-CNN: High Quality Object Detection and Instance Segmentationhttps://github.com/zhaoweicai/cascade-rcnn
2017ICCVFocal Loss for Dense Object Detectionhttps://github.com/open-mmlab/mmdetection
2016ECCVSSD: Single Shot MultiBox Detectorhttps://github.com/weiliu89/caffe
2015NIPSFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkshttps://github.com/ShaoqingRen/faster_rcnn
2015ICCVFast R-CNNhttps://github.com/rbgirshick/fast-rcnn

2.YOLO系列

DatePub.TitleCode
2023YOLOV8https://github.com/ultralytics/ultralytics
2022DAMO-YOLOhttps://github.com/tinyvision/DAMO-YOLO
2022arXivYOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorshttps://github.com/wongkinyiu/yolov7
2022Yolov6https://github.com/meituan/YOLOv6
2022arXivPP-YOLOE: An evolved version of YOLOhttps://github.com/PaddlePaddle/PaddleDetection
2021Tech ReportYOLOX: Exceeding YOLO Series in 2021https://github.com/Megvii-BaseDetection/YOLOX
2021aiXivYou Only Learn One Representation: Unified Network for Multiple Taskshttps://github.com/WongKinYiu/yolor
2021CVPRScaled-YOLOv4: Scaling Cross Stage Partial Networkhttps://github.com/WongKinYiu/ScaledYOLOv4
2021arXivPP-YOLOv2: A Practical Object Detectorhttps://github.com/PaddlePaddle/PaddleDetection
2020arXivPP-YOLO: An Effective and Efficient Implementation of Object Detectorhttps://github.com/PaddlePaddle/PaddleDetection
2020Yolov5https://github.com/ultralytics/yolov5
2020arXivYolov4: Optimal speed and accuracy of object detectionhttps://github.com/AlexeyAB/darknet
2018Tech ReportYOLOv3: An Incremental Improvement
2017CVPRYOLO9000: Better, Faster, Stronger
2016CVPRYou Only Look Once: Unified, Real-Time Object Detection

3.分类与回归不一致问题

DatePub.TitleCode
2021ICCVTOOD: Task-aligned One-stage Object Detectionhttps://github.com/fcjian/TOOD
2021ICCVReconcile Prediction Consistency for Balanced Object Detection
2021ICCVMutual Supervision for Dense Object Detection
2020CVPRRethinking Classification and Localization for Object Detectionhttps://github.com/wuyuebupt/doubleheadsrcnn
2020CVPRMultiple Anchor Learning for Visual Object Detectionhttps://github.com/KevinKecc/MAL

4.标签分配

DatePub.TitleCode备注
2023CVPROne-to-Few Label Assignment for End-to-End Dense Detectionhttps://github.com/strongwolf/o2f
2022CVPRA Dual Weighting Label Assignment Scheme for Object Detectionhttps://github.com/strongwolf/dw
2021NeurocomputingLLA: Loss-aware Label Assignment for Dense Pedestrian Detectionhttps://github.com/Megvii-BaseDetection/LLA笔记
2021CVPRIQDet: Instance-wise Quality Distribution Sampling for Object Detection
2021CVPROTA: Optimal Transport Assignment for Object Detectionhttps://github.com/Megvii-BaseDetection/OTA
2020ECCVProbabilistic Anchor Assignment with IoU Prediction for Object Detectionhttps://github.com/kkhoot/PAA
2020CVPRBridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectionhttps://github.com/sfzhang15/ATSS
2020arXivAutoAssign: Differentiable Label Assignment for Dense Object Detectionhttps://github.com/Megvii-BaseDetection/AutoAssign
2019NIPSFreeAnchor: Learning to Match Anchors for Visual Object Detectionhttps://github.com/zhangxiaosong18/FreeAnchor
2019CVPRRegion Proposal by Guided Anchoring
2018NIPSMetaAnchor: Learning to Detect Objects with Customized Anchors-

5.DETR系列

DatePub.TitleCode
2023arXivRT-DETR: DETRs Beat Yolos on Real-time Object Detectionhttps://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/rtdetr#%E6%A8%A1%E5%9E%8B
2022CVPRDN-DETR: Accelerate DETR Training by Introducing Query DeNoisinghttps://github.com/fengli-ust/dn-detr
2021ICLRDeformable DETR: Deformable Transformers for End-to-End Object Detectionhttps://github.com/fundamentalvision/Deformable-DETR
2021ICCVRethinking Transformer-based Set Prediction for Object Detectionhttps://github.com/edward-sun/tsp-detection
2021ICCVDynamic DETR: End-to-End Object Detection with Dynamic Attention
2020ECCVEnd-to-End Object Detection with Transformershttps://github.com/facebookresearch/detr

6.知识蒸馏

DatePub.TitleCode
2022CVPRLocalization Distillation for Dense Object Detectionhttps://github.com/HikariTJU/LD
2022CVPRFocal and Global Knowledge Distillation for Detectorshttps://github.com/yzd-v/FGD
2022WACVImproving Object Detection by Label Assignment Distillationhttps://github.com/cybercore-co-ltd/CoLAD
2021CVPRDistilling Object Detectors via Decoupled Featureshttps://github.com/ggjy/DeFeat.pytorch
2021CVPRGeneral Instance Distillation for Object Detection

7.FPN相关

DatePub.TitleCode
2022ECCVYou Should Look at All Objectshttps://github.com/charlespikachu/yslao
2021CVPRYou Only Look One-level Featurehttps://github.com/megvii-model/YOLOF
2019CVPRFeature Selective Anchor-Free Module for Single-Shot Object Detectionhttps://github.com/open-mmlab/mmdetection

8.小目标检测系列

DatePub.TitleCode
2023arXivTinyDet: Accurate Small Object Detection in Lightweight Generic Detectorshttps://github.com/hustvl/TinyDet
2022ECCVRFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detectionhttps://github.com/chasel-tsui/mmdet-rfla
2022CVPRQueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detectionhttps://github.com/ChenhongyiYang/QueryDet-PyTorch
2020TSMCA Survey of the Four Pillars for Small Object Detection: Multiscale Representation, Contextual Information, Super-Resolution, and Region Proposal

9.数据增强

DatePub.TitleCode
2021CVPRScale-aware Automatic Augmentation for Object Detectionhttps://github.com/dvlab-research/SA-AutoAug

10.开放世界目标检测

DatePub.TitleCode
2021CVPRTowards Open World Object Detectionhttps://github.com/JosephKJ/OWOD

11.长尾目标检测

DatePub.TitleCode
2021ICCVExploring Classification Equilibrium in Long-Tailed Object Detectionhttps://github.com/fcjian/loce
2021ICCVMOSAICOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detectionhttps://github.com/czhang0528/MosaicOS

12. 单点目标检测

DatePub.TitleCode
2022ECCVPoint-to-Box Network for Accurate Object Detection via Single Point Supervisionhttps://github.com/ucas-vg/P2BNet

13. 红外目标检测

DatePub.TitleCode
2022CVPRTarget-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detectionhttps://github.com/JinyuanLiu-CV/TarDAL
2022ECCVMultimodal Object Detection via Probabilistic Ensemblinghttps://github.com/Jamie725/RGBT-detection

14. 探讨类

DatePub.TitleCode
2022arXivUnderstanding CNN Fragility When Learning With Imbalanced Data
2022arXivTSAA: A Two-Stage Anchor Assignment Method towards Anchor Drift in Crowded Object Detection
2019arXivEmpirical Upper Bound in Object Detection and More

15. diffusion

DatePub.TitleCode
2022arXivDiffusionDet: Diffusion Model for Object Detectionhttps://github.com/shoufachen/diffusiondet

16. Loss相关

DatePub.TitleCode
2021arXivFocal and Efficient IOU Loss for Accurate Bounding Box Regression
2021arXivAlpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regressionhttps://github.com/jacobi93/alpha-iou
2020AAAIDistance-IoU Loss: Faster and Better Learning for Bounding Box Regressionhttps://github.com/Zzh-tju/DIoU
2019CVPRGeneralized Intersection over Union: A Metric and A Loss for Bounding Box Regression-
  • 12
    点赞
  • 51
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

gorgeous(๑>؂<๑)

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值