RIFormer: Keep Your Vision Backbone Effective But Removing Token Mixer-Reference-Cited by-同舟云学术

RIFormer: Keep Your Vision Backbone Effective But Removing Token Mixer

Published:2023-06 Issue: Volume: Page:
ISSN:
Container-title:2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Wang Jiahao¹,Zhang Songyang¹,Liu Yong²,Wu Taiqiang²,Yang Yujiu²,Liu Xihui³,Chen Kai¹,Luo Ping³,Lin Dahua¹

Affiliation:

1. Shanghai AI Laboratory

2. Tsinghua Shenzhen International Graduate School

3. The University of HongKong

Funder

National Key R&D Program of China

National Natural Science Foundation of China

Publisher

IEEE

Link

Reference52 articles.

3. Vision gnn: An image is worth graph of nodes;han;NeurIPS,0

4. An image is worth 16×16 words: Transformers for image recognition at scale;dosovitskiy;ICLRE,0

Cited by 9 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

4. A Reconfigurable Framework for Neural Network Based Video In-Loop Filtering;ACM Transactions on Multimedia Computing, Communications, and Applications;2024-03-08

5. Pollen dictionary construction based on supervised comparative learning;Proceedings of the 3rd International Conference on Computer, Artificial Intelligence and Control Engineering;2024-01-26