GitHub：Anchor-free目標檢測最全資料集錦

2020-09-16 00:30:04.0

作者：Amusi
Date：2020-09-05
來源： CVer微信公衆號
原文： GitHub：Anchor-free目標檢測最全資料集錦

前言

Anchor-free 目標檢測 無疑是近一兩年內目標檢測非常重要的研究方向之一，Amusi 覺得特別是得益於DenseBox、CornerNet、FCOS和CenterNet等網絡的創新性提出。

近兩年裏，CVPR 2019、ICCV 2019、CVPR 2020和ECCV 2020上出現了不少anchor-free目標檢測的優質工作。"先富帶後富"，近來也有若干anchor-free目標跟蹤網絡的提出。

Amusi 在本文要分享的是目前最全，最新的anchor-free目標檢測論文合集。

Anchor-free目標檢測

項目作者：Xin Zhang, Xuesong Wang, nuo xu

本項目共計涵蓋 24篇anchor-free目標檢測論文，其中論文大多爲頂會且已開源！

[arXiv] AutoAssign: Differentiable Label Assignment for Dense Object Detection.
[arXiv] RepPoints V2: Verification Meets Regression for Object Detection. [pytorch]
[ECCV] Corner Proposal Network for Anchor-free, Two-stage Object Detection. [Available soon]
[ECCV] HoughNet: Integrating near and long-range evidence for bottom-up object detection. [pytorch]
[CVPR] Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection. [pytorch]
[CVPR] Soft Anchor-Point Object Detection. [Keras]
[CVPR] CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection. [pytorch]
[arXiv] SaccadeNet: A Fast and Accurate Object Detector. [pytorch]
[arXiv] Localization Uncertainty Estimation for Anchor-Free Object Detection.
[ECCV] Dense RepPoints: Representing Visual Objects with Dense Point Sets. [pytorch]
[ECCV] BorderDet: Border Feature for Dense Object Detection. [pytorch]
[arXiv] Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection. [pytorch]

[ICCV] RepPoints: Point Set Representation for Object Detection. [pytorch]
[arXiv] Segmentation is All You Need.
[arXiv] FCOS: Fully Convolutional One-Stage Object Detection. [pytorch]
[arXiv] CenterNet: Keypoint Triplets for Object Detection. [pytorch]
[arXiv] Objects as Points. [pytorch]
[arXiv] FoveaBox: Beyond Anchor-based Object Detector. [pytorch]
[CVPR] Feature Selective Anchor-Free Module for Single-Shot Object Detection. [pytorch]
[arXiv] ExtremeNet: Bottom-up Object Detection by Grouping Extreme and Center Points. [pytorch]

[ECCV] CornerNet: Detecting Objects as Paired Keypoints. [pytorch]
[arXiv] An Anchor-Free Region Proposal Network for Faster R-CNN based Text Detection Approaches.

[CVPR] You Only Look Once: Unified, Real-Time Object Detection. [tensorflow] [darknet]
[acm multimedia] UnitBox: An Advanced Object Detection Network. [tensorflow]

[arXiv] DenseBox: Unifying Landmark Localization with End to End Object Detection. [caffe]

一份超級棒的Anchor-free 目標檢測學習資料，強烈推薦大家學習！

另外強烈推薦閱讀，Amusi 整理過的最全資料系列如下：

推薦大家關注計算機視覺論文速遞知乎專欄和CVer微信公衆號，可以快速瞭解到最新優質的CV論文。