He and colleagues: masked autoencoders for scalable vision learning

What changed

Used visible-patch encoder and lightweight decoder to reconstruct masked image patches.

Scientific scope

The record is the exact six-author CVPR 2022 paper. It does not absorb language masked modeling, all image autoencoders, later MAE variants or performance claims outside the reported models, data and evaluations.

Evidence

The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact six-author CVPR 2022 paper. It does not absorb language masked modeling, all image autoencoders, later MAE variants or performance claims outside the reported models, data and evaluations.

Contributors

• Kaiming He · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Xinlei Chen · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Saining Xie · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Yanghao Li · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Piotr Dollár · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Ross Girshick · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.

• CVF open-access paper for masked autoencoders

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction