MST: Masked Self-Supervised Transformer for Visual Representation

The proposed method is a self-supervised learning approach for visual representation learning, which can explicitly capture the local context of an image while preserving the global semantic information.

Data and Resources

Cite this as

Fan Yang, Wei Li, Yousong Zhu, Zhaowen Li, Zhiyang Chen, Chaoyang Zhao, Rui Deng, Liwei Wu, Rui Zhao, Ming Tang, Jinqiao Wang (2024). Dataset: MST: Masked Self-Supervised Transformer for Visual Representation. https://doi.org/10.57702/i8tw1h75

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Fan Yang
More Authors
Wei Li
Yousong Zhu
Zhaowen Li
Zhiyang Chen
Chaoyang Zhao
Rui Deng
Liwei Wu
Rui Zhao
Ming Tang
Jinqiao Wang