search

Kevinz-code / CSRA

Official code of ICCV2021 paper "Residual Attention: A Simple but Effective Method for Multi-Label Recognition"
GNU Affero General Public License v3.0
212 stars 37 forks source link

Is the code consistent with the description in the paper? #5

Closed AlphaPlusTT closed 2 years ago

AlphaPlusTT commented 3 years ago

According to formula 5 and formula 6 in the paper, the class-specific residual attention (CSRA) feature f should be sent to the classifier to obtain the final logits, but in your code, you use the f as the final logits, what's the difference?

Kevinz-code commented 3 years ago

Hi, @AlphaPlusTT

Actually there are no difference and the code is consistent with the paper.

The logit for the i-th class can be expressed by Eq. (7) and Eq. (8) in the paper (in which ''x_k \cdot m_i'' can be replaced by s_k^i ), so the form of the second term of Eq. (8) is equal to the line 26 at "pipeline/csra.py''.

Best, Authors

AlphaPlusTT commented 3 years ago

Thanks for your reply. I try to use your method for pedestrian attribute recognition task with dataset rapv2, but the CSRA dose not work. Do you have any suggestions?

abhigoku10 commented 3 years ago

@AlphaPlusTT i am also trying the same on PETA dataset and facing error , what error are you facing ? @Kevinz-code pls do share ur thoughts

Kevinz-code commented 3 years ago

@abhigoku10 @AlphaPlusTT Thanks for reading.

  1. Actually we didn't run CSRA model on rapv2 and PETA, which weren't the popular multi-label recognition datasets in relevant literatures.

  2. We are not sure what "error" or "does not work" in your own implementation. Say, does the improvement of CSRA is low in comparison with the baseline method? It is advised that you provide the training details like model name, data aug, hyper-params, mAP, etc.

  3. In our implementation in Wider-Attribute, the improvement is consistent by using VIT models, you can try VIT models and use hyper-parameters similar to our code as well.

Best,