cmhungsteve/Awesome-Transformer-Attention

Transformer on Sample Relationship Exploration

zhihou7 opened this issue · 3 comments

zhihou7 commented

Hi, Thanks for your conclusion!

I think our recent work might be also a typical Transformer Attention for sample relationship exploration: CVPR2022, BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning, https://arxiv.org/abs/2203.01522. There is also a general version in BatchFormerV2, in which we present the consistent effectiveness on object detection, panoptic segmentation, and image classification.

If you also think so, it would be better to include this paper.

Regards,

cmhungsteve commented

Hello @zhihou7,
This list already includes the two papers you mentioned above.
Thank you.

zhihou7 commented

Sincerely sorry for that. Thank you very much. I merely checked the list in Transfer Learning (domain generalization). Btw, BatchFormerV2 is closer to object detection since this paper is verified to be plug-and-play to DETR-based methods with massive experiments.

Regards,

  • 👍1
cmhungsteve commented

Thank you for your suggestion.
Actually, I plan to reorganize the categories of the list in the near future to make it better categorize the papers.

  • 👍1