论文 | long-tailed recognition typ

作者: 与阳光共进早餐 | 来源:发表于2021-02-24 21:16 被阅读0次

    一 写在前面

    未经允许,不得转载,谢谢~~

    最近想看看long-tailed recognition是如何处理imbalanced dataset的,对查阅到比较有用的资料做了一个整理和记录。

    二 overview

    2.1 基本问题介绍

    大多数我们用的benchmark都是类别均衡的(每个类别的标注样本数一致),但是事实上自然界中的物体很可能是一个类别均衡的分布,常见类别样本多,稀有类别样本少,更直观的解释可以看下面这张图。


    long-tailed recognition解决的就是数据呈现这样长尾分布时候的识别问题。

    2.2 资料推荐

    这边推荐两个我觉得很不错的link

    三 typical paper list

    根据现有的四大类方法(re-sampling,re-weighting,transfer learning,else),综合根据以上的资料和文章的引用量,code开源等情况整理了以下list,供需要的同学使用~

    3.1 re-sampling

    通过影响样本采样频率来达到balance,又可以分为头部类别欠采样(under-sampling)和尾部类别过采样(over-sampling)两个细分类别。

    paper:ICLR2020: Decoupling Representation and Classifier for Long-Tailed Recognition, ICLR 2020 (star300+)

    paper:BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition,CVPR 2020 (star300+)

    3.2 re-weighting

    此类方法主要表现在分类loss上,对loss进行加权。

    paper:Class-Balanced Loss Based on Effective Number of Samples,CVPR 2019 (star300+)

    paper:Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss,NIPS 2019(star300+)

    3.3 transfer learning

    希望将知识从头部类迁移到尾部类别。

    paper:Large-Scale Long-Tailed Recognition in an Open World,CVPR 2019 (star500+)

    paper:Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective,CVPR 2020

    paper:Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification,ECCV 2020

    3.4 else

    paper:Long-tailed Recognition by Routing Diverse Distribution-Aware Experts, arxiv 2020

    paper:ResLT: Residual Learning for Long-tailed Recognition,arxiv2021

    相关文章

      网友评论

        本文标题:论文 | long-tailed recognition typ

        本文链接:https://www.haomeiwen.com/subject/xtlefltx.html