Awesome-Anchor-Free-Object-Detection

🔥🔥🔥 This repository lists some awesome Anchor-Free object detection series projects.

Contents

• Awesome-Anchor-Free-Object-Detection
  • Frameworks
  • Applications
  • Others

Frameworks

• YOLO (Darknet ) : "You Only Look Once: Unified, Real-Time Object Detection". (CVPR 2016)

• CornerNet : "CornerNet: Detecting Objects as Paired Keypoints". (ECCV 2018)

• xingyizhou/CenterNet : "Objects as Points". (arXiv 2019)

• Duankaiwen/CenterNet : "CenterNet: Keypoint Triplets for Object Detection". (ICCV 2019)

• FreeAnchor : "FreeAnchor: Learning to Match Anchors for Visual Object Detection". (NeurIPS 2019)

• FCOS : "FCOS: Fully Convolutional One-Stage Object Detection". (ICCV 2019, IEEE TPAMI 2021)

• ExtremeNet : "Bottom-up Object Detection by Grouping Extreme and Center Points". (CVPR 2019)

• RepPoints : "Bottom-up Object Detection by Grouping Extreme and Center Points". (ICCV 2019)

• CenterNet3d : "CenterNet3D: An Anchor free Object Detector for Autonomous Driving". (arXiv 2020)

• CenterMask : "CenterMask: Real-Time Anchor-Free Instance Segmentation". (CVPR 2020)

• AutoAssign : "AutoAssign: Differentiable Label Assignment for Dense Object Detection". (arXiv 2020)

• BorderDet : "BorderDet: Border Feature for Dense Object Detection". (ECCV 2020)

• Dense-RepPoints : "Dense Reppoints: Representing Visual Objects with Dense Point Sets". (ECCV 2020)

• sfzhang15/ATSS : "Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection". (CVPR 2020)

• RepPointsV2 : "RepPoints V2: Verification Meets Regression for Object Detection". (NeurIPS 2020)

• GFocal : "Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection". (NeurIPS 2020)

• DETR : "End-to-end object detection with transformers". (ECCV 2020)

• CenterNet2 : "Probabilistic two-stage detection". (arXiv 2021)

• OneNet : "What Makes for End-to-End Object Detection?". (ICML 2021)

• Sparse R-CNN : "Sparse R-CNN: End-to-End Object Detection with Learnable Proposals". (CVPR 2021)

• DeFCN : "End-to-End Object Detection with Fully Convolutional Network". (CVPR 2021)

• YOLOX : "YOLOX: Exceeding YOLO Series in 2021". (arXiv 2021)

• YOLOR : "You Only Learn One Representation: Unified Network for Multiple Tasks". (arXiv 2021)

• DAFNe : "DAFNe: A One-Stage Anchor-Free Deep Model for Oriented Object Detection". (arXiv 2021)

• FCAF3D : "FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection". (arXiv 2021)

• NanoDet-Plus : NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥.

• AlignPS : "Anchor-Free Person Search". (CVPR 2021)

• ByteTrack : "ByteTrack: Multi-Object Tracking by Associating Every Detection Box". (arXiv 2021)

• FII-CenterNet : "FII-CenterNet: An Anchor-Free Detector With Foreground Attention for Traffic Object Detection". (IEEE TVT 2021)

• CenterNet++ : "CenterNet++ for Object Detection". (arXiv 2022)

• dog-qiuqiu/FastestDet : ⚡ A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is simpler. (知乎 2022)

• AIRDet : Welcome to AIRDet! AIRDet is an efficiency-oriented anchor-free object detector, aims to enable robust object detection in various industry scene.

• YOLOv6 : "YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications". (arXiv 2022). "微信公众号「美团技术团队」《YOLOv6：又快又准的目标检测框架开源啦》"。 "微信公众号「美团技术团队」《目标检测开源框架YOLOv6全面升级，更快更准的2.0版本来啦 》"。 "微信公众号「集智书童」《超越YOLOv7 | YOLOv6论文放出，重参+自蒸馏+感知量化+...各种Tricks大放异彩》"

• YOLOX-PAI : "YOLOX-PAI: An Improved YOLOX, Stronger and Faster than YOLOv6". (arXiv 2022). "微信公众号「集智书童」《YOLOX升级 | 阿里巴巴提出YOLOX-PAI，1ms内精度无敌，超越YOLOv6、PP-YOLOE》"

Applications

• TracKit : "Ocean: Object-aware Anchor-free Tracking". (ECCV 2020)

• CenterTrack : "Tracking Objects as Points". (ECCV 2020)

• FairMOT : "FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking". (IJCV 2021)

• TraDeS : "Track to Detect and Segment: An Online Multi-Object Tracker". (CVPR 2021)

• DSFNet : "DSFNet: Dynamic and Static Fusion Network for Moving Object Detection in Satellite Videos". (IEEE Geoscience and Remote Sensing Letters 2021)

• CaptainEven/MCMOT : Real time one-stage multi-class & multi-object tracking based on anchor-free detection and ReID.

• DataXujing/CornerNet-Lite-Pytorch : 🚨🚨🚨 CornerNet:基于虚拟仿真环境下的自动驾驶交通标志识别。

• HaiNguyen2903/CenterFace : Using free anchor method to solve Object Detection problem.

• Bigtuo/YOLOX-Lite : 将YOLOv5-Lite代码中的head更换为YOLOX head。

• DSFNet : "DSFNet: Dynamic and Static Fusion Network for Moving Object Detection in Satellite Videos". (IEEE Geoscience and Remote Sensing Letters 2021)

Others

• XinZhangNLPR/awesome-anchor-free-object-detection : In this project, we focus on collection the anchor free object detection paper or code.

• VCBE123/AnchorFreeDetection : list the paper for recently anchor free detector.