AWhat changed
Pretrained vision Transformers by predicting discrete visual tokens for masked image patches, transferring the learned encoder to image classification and segmentation.
Scientific scope
Pretrained vision Transformers by predicting discrete visual tokens for masked image patches, transferring the learned encoder to image classification and segmentation. Inherits BERT-style masking, vision Transformers and visual tokenization. Not a proof of universal superiority over pixel reconstruction or contrastive learning.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Inherits BERT-style masking, vision Transformers and visual tokenization. Not a proof of universal superiority over pixel reconstruction or contrastive learning.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- BEiT: BERT Pre-Training of Image Transformers
- Bao et al.: BEiT masked visual-token prediction — official implementation
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