search

KaihuaTang / Long-Tailed-Recognition.pytorch

[NeurIPS 2020] This project provides a strong single-stage baseline for Long-Tailed Classification, Detection, and Instance Segmentation (LVIS). It is also a PyTorch implementation of the NeurIPS 2020 paper 'Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect'.
GNU General Public License v3.0
555 stars 68 forks source link

Migration to multi label long tailed recognition #30

Open AlphaPlusTT opened 3 years ago

AlphaPlusTT commented 3 years ago

Thank you for your excellent work. I want to try to migrate the classifier (CausalNormClassifier) in this work to the task of multi label long tailel recognition. However, the following problems appeared. I believe the model has not learned any knowledge at all, perhaps the output is smoothed out in the inference stage. Because the loss change during training seems normal. Can you give me some advice or tell me the possible problems?

感谢你开源这么优秀的工作，我想尝试把这个工作中的分类器迁移到多标签长尾数据分类任务中去，但是却出现了如下的问题，感觉模型完全没有学习到任何知识，或者好像是在推理的阶段输出被平滑抵消掉了？因为在训练过程中的loss变化看起来是正常的。能否给我一些建议或者告诉我可能出现的问题？

捕获

AlphaPlusTT commented 3 years ago

Could it be the difference between softmax and sigmoid that affects the results？

jsetty commented 2 years ago

Thank you for your excellent work. I want to try to migrate the classifier (CausalNormClassifier) in this work to the task of multi label long tailel recognition. However, the following problems appeared. I believe the model has not learned any knowledge at all, perhaps the output is smoothed out in the inference stage. Because the loss change during training seems normal. Can you give me some advice or tell me the possible problems?

感谢你开源这么优秀的工作，我想尝试把这个工作中的分类器迁移到多标签长尾数据分类任务中去，但是却出现了如下的问题，感觉模型完全没有学习到任何知识，或者好像是在推理的阶段输出被平滑抵消掉了？因为在训练过程中的loss变化看起来是正常的。能否给我一些建议或者告诉我可能出现的问题？

捕获

Hi @AlphaPlusTT ,

Did you manage to find a solution for multi-label long tail classification?

Thanks