[如何缓解长尾分布问题?]Decoupling representation and classifier for long-tailed recognition
今天给大家分享一篇来自ICLR 2020中Facebook的一篇文章，通过采用两步训练的方式来缓解长尾分布带来的问题，视频中我讨论了第一步的采样方式和第二步训练线性分类器的方法，欢迎大家评论区讨论指正。
Watch video [如何缓解长尾分布问题?]Decoupling representation and classifier for long-tailed recognition online, duration hours minute second in high quality that is uploaded to the channel ChrisTech 20 June 2021. Share the link to the video on social media so that your subscribers and friends will also watch this video. This video clip has been viewed 127 times and liked it 0 visitors.
![[如何解决样本不均衡与难样本问题?]Focal Loss for Dense Object Detection](https://images.reviewsvideo.ru/videos/aSAGerkXjps)
![[2021达摩院最新paper:对Focal loss改进]Asymmetric Loss For Multi-Label Classification](https://images.reviewsvideo.ru/videos/GACSQKF15j0)
![[如何缓解长尾分布问题?]Decoupling representation and classifier for long-tailed recognition](https://images.reviewsvideo.ru/videos/v_PlRekD358)
