Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

多标签分类任务ML-Decoder论文复现 #2896

Open
zhangyubo0722 opened this issue Aug 3, 2023 · 0 comments
Open

多标签分类任务ML-Decoder论文复现 #2896

zhangyubo0722 opened this issue Aug 3, 2023 · 0 comments
Assignees

Comments

@zhangyubo0722
Copy link
Collaborator

zhangyubo0722 commented Aug 3, 2023

背景

经过前沿技术调研与讨论,我们最终确定了ML-Decoder任务,该论文提出的可扩展通用分类头在多标签分类、zero-sho以及单标签分类任务上表现出很好的效果。本任务的完成可以扩充PaddleClas多标签分类相关视觉任务,并有众多应用场景。
作者团队基于不同数据集验证不同任务的性能,充分证明ML-Decoder分类头的性能以及泛用性。
现已有开源代码并提供了预训练权重,该论文需复现出resnet101的多标签分类部分,训练指标对齐。

解决步骤

  1. 根据开源代码进行网络结构、评估指标转换。代码链接:https://github.com/Alibaba-MIIL/ML_Decoder
  2. 结合论文复现指南,对多标签分类部分进行前反向对齐等操作,并复现多标签分类指标,ResNet101训练精度达到论文Table.5中的mAP为87.1%,多标签分类训练方式可参考文档
图片
  1. 参考PR提交规范提交代码PR到PaddleClas中。

数据集:MS-COCO

图片
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants