目标检测中的不平衡问题及解决方案论文汇总

转载自https://github.com/kemaloksuz/ObjectDetectionImbalance

A Repository of the Papers Addressing Imbalance Problems in Object Detection

This repository provides an up-to-date the list of studies addressing imbalance problems in object detection. It follows the taxonomy provided in the following paper(please cite the paper if you benefit from this repository):

K. Oksuz, B. C. Cam, S. Kalkan, E. Akbas, “Imbalance Problems in Object Detection: A Review”, (under review), 2019.[preprint]

Table of Contents (Follows the taxonomy in the paper)

  1. Class Imbalance
    1.1 Foreground-Backgorund Class Imbalance
    1.2 Foreground-Foreground Class Imbalance
  2. Scale Imbalance
    2.1 Object/box-level Scale Imbalance
    2.2 Feature-level Imbalance
  3. Spatial Imbalance
    3.1 Imbalance in Regression Loss
    3.2 IoU Distribution Imbalance
    3.3 Object Location Imbalance
  4. Objective Imbalance

1. Class Imbalance

1.1. Foreground-Backgorund Class Imbalance

  • Hard Sampling Methods
    • Random Sampling
    • Hard Example Mining
      • Bootstrapping, NeurIPS 1996, [paper]
      • SSD, ECCV 2016, [paper]
      • Online Hard Example Mining, CVPR 2016, [paper]
      • IoU-based Sampling, CVPR 2019, [paper]
    • Limit Search Space
      • Two-stage Object Detectors
      • IoU-lower Bound, ICCV 2015, [paper]
      • Objectness Prior, CVPR 2017, [paper]
      • Negative Anchor Filtering, CVPR 2018, [paper]
      • Objectness Module, ICCV 2019, [paper]
  • Soft Sampling Methods
    • Focal Loss, ICCV 2017, [paper]
    • Gradient Harmonizing Mechanism, AAAI 2019, [paper]
    • Prime Sample Attention, arXiv 2019, [paper]
  • Sampling-Free Methods
    • Is Sampling Heuristics Necessary in Training Deep Object Detectors?, arXiv 2019, [paper]
    • Residual Objectness for Imbalance Reduction, arXiv 2019, [paper]
    • AP Loss, CVPR 2019, [paper]
    • DR Loss, arXiv 2019, [paper]
  • Generative Methods
    • Adversarial Faster-RCNN, CVPR 2017, [paper]
    • Task Aware Data Synthesis, CVPR 2019, [paper]
    • PSIS, arXiv 2019, [paper]
    • Bounding Box Generator, WACV 2020, [paper]

1.2. Foreground-Foreground Class Imbalance

  • Fine-tuning Long Tail Distribution for Obj.Det., CVPR 2016, [paper]
  • PSIS, arXiv 2019, [paper]
  • OFB Sampling, WACV 2020, [paper]

2. Scale Imbalance

2.1. Object/box-level Scale Imbalance

  • Methods Predicting from the Feature Hierarchy of Backbone Features

    • Scale-dependent Pooling, CVPR 2016, [paper]
    • SSD, ECCV 2016, [paper]
    • Multi Scale CNN, ECCV 2016, [paper]
    • Scale Aware Fast R-CNN, IEEE Transactions on Multimedia, 2018 [paper]
  • Methods Based on Feature Pyramids

    • FPN, CVPR 2017, [paper]
    • See feature-level imbalance methods
  • Methods Based on Image Pyramids

  • Methods Combining Image and Feature Pyramids

    • Efficient Featurized Image Pyramids, CVPR 2019, [paper]
    • Enriched Feature Guided Refinement Network, ICCV 2019, [paper]
    • Super-Resolution for Small Objects, ICCV 2019, [paper]
    • Scale Aware Trident Network, ICCV 2019, [paper]

2.2. Feature-level Imbalance

  • Methods Using Pyramidal Features as a Basis

  • Methods Using Backbone Features as a Basis

3. Spatial Imbalance

3.1. Imbalance in Regression Loss

  • Lp norm based

  • IoU based

    • IoU Loss, ACM IMM 2016, [paper]
    • Bounded IoU Loss, CVPR 2018, [paper]
    • Generalized IoU Loss, CVPR 2019, [paper]
    • Distance IoU Loss, AAAI 2020, [paper]
    • Complete IoU Loss, AAAI 2020, [paper]

3.2. IoU Distribution Imbalance

  • Cascade R-CNN, CVPR 2018, [paper]
  • Hierarchical Shot Detector, ICCV 2019, [paper]

3.3. Object Location Imbalance

4. Objective Imbalance

  • Task Weighting
  • Classification Aware Regression Loss, arXiv 2019, [paper]
  • Guided Loss, arXiv 2019, [paper]
  • 1
    点赞
  • 6
    收藏
    觉得还不错? 一键收藏
  • 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
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