발표를 위해 준비했던 PPT Slides를 사용해 Vision Transformer with Deformable Attention, CVPR'22를 정리해 리뷰합니다.
Arxiv Paper Link: https://arxiv.org/abs/2309.01430
Official GitHub Link: https://github.com/LeapLabTHU/DAT
'AI' 카테고리의 다른 글
| OpenSEED: A Simple Framework for Open-Vocabulary Segmentation and Detection (0) | 2024.11.06 |
|---|---|
| Morphing Tokens Draw Strong Masked Image Models (0) | 2024.11.05 |
| Deformable DETR: Deformable Transformers for End-to-End Object Detection (0) | 2023.09.19 |
| DCN: Deformable Convolutional Networks (0) | 2023.09.19 |
| Deformable Video Transformer (0) | 2023.09.19 |
