
Index
DETR の改善手法.
Deformable Attention Module の提案.
Deformable CNN から着想.
Attention Module が、重点的に注意を払うポイントは、
入力される Feature Map のサイズに関わらず、基準点の周辺となる.
Deformable Attention Transformer との関連は?
- Deformable Attention Transformer / DAT
その他の工夫
Iterative Bounding Box Refinement
- Raft: Recurrent all-pairs field transforms for optical flow.
参考
- Deformable DETR: Deformable Transformers for End-to-End Object Detection
- [2020 SenseTime Research]
- v4
- 2 RELATED WORK
- Efficient Attention Mechanism
- Multi-scale Feature Representation for Object Detection
- 3 REVISITING TRANSFORMERS AND DETR
- Multi-Head Attention in Transformers
- DETR
- 4 METHOD
- 4.1 DEFORMABLE TRANSFORMERS FOR END-TO-END OBJECT DETECTION
- Deformable Attention Module
- Multi-scale Deformable Attention Module
- Deformable Transformer Encoder
- Deformable Transformer Decoder
- 4.2 ADDITIONAL IMPROVEMENTS AND VARIANTS FOR DEFORMABLE DETR
- Iterative Bounding Box Refinement
- Two-Stage Deformable DETR
- arxiv.org
Web サイト