首页|期刊导航|计算可视媒体（英文）|FastMAE:Efficient masked autoencoder with offline tokenizer

FastMAE:Efficient masked autoencoder with offline tokenizer

Meng-Hao Guo Chen Wang Wei Liu Shi-Min Hu

计算可视媒体（英文）2025，Vol.11Issue(3)：483-496,14.

计算可视媒体（英文）2025，Vol.11Issue(3)：483-496,14.DOI:10.26599/CVM.2025.9450474

FastMAE:Efficient masked autoencoder with offline tokenizer

Meng-Hao Guo ¹Chen Wang ²Wei Liu ³Shi-Min Hu¹

作者信息

1. Department of Computer Science,Tsinghua University,Beijing 100084,China
2. University of Pennsylvania,Philadelphia,PA 19104,USA
3. Tencent Data Platform,Shenzhen 518057,China
折叠

摘要

关键词

deep learning/computer vision/masked image modeling(MIM)

Key words

deep learning/computer vision/masked image modeling(MIM)

引用本文复制引用

Meng-Hao Guo,Chen Wang,Wei Liu,Shi-Min Hu..FastMAE:Efficient masked autoencoder with offline tokenizer[J].计算可视媒体（英文）,2025,11(3):483-496,14.

基金项目

This work was supported by the National Science and Technology Major Project(Grant No.2021ZD0112902),the National Natural Science Foundation of China(Grant Nos.623B2057 and 62220106003),Tsinghua University Initiative Scientific Research Program,and Tsinghua-Tencent Joint Laboratory for Internet Innovation Technology.The authors sincerely appreciate the dedicated effort and valuable feedback from the anonymous reviewers and editor,which significantly improved the manuscript. （Grant No.2021ZD0112902）

计算可视媒体（英文）

访问量0

下载量0

段落导航