1. Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers;zheng,2020
2. Exploring self-attention for image recognition;zhao;Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,2020
3. Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection
4. Resnest: Split-attention networks;zhang,2020
5. Deformable fdetrg: Deformable transformers for end-to-end object detection;zhu;International Conference on Learning Representations,2021