Learning Decorrelated Representations Efficiently Using Fast Fourier Transform

Shigeto, Y; Shimbo, M; Yoshikawa, Y; Takeuchi, A

Shigeto, Y (通讯作者)，Chiba Inst Technol, STAIR Lab, Narashino, Chiba, Japan.

2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR, 2023; (): 2052

Abstract

Barlow Twins and VICReg are self-supervised representation learning models that use regularizers to decorrelate features. Although these models are as......

Full Text Link


Links

期刊讨论 | 中国SCI论文 | 期刊主页 | 投稿经验 | 杂志官网 | 投稿链接 | 作者需知 | PMC链接 | Pubmed全文检索