Dosovitskiy and colleagues: Vision Transformer image-patch classification

What changed

Applied a pure transformer to sequences of image patches for classification, reporting strong transfer after large-scale image pretraining.

Scientific scope

Applied a pure transformer to sequences of image patches for classification, reporting strong transfer after large-scale image pretraining. Scope limitation: This is the 2020 ViT preprint, later published at ICLR 2021; results depend on large-scale pretraining and studied recognition benchmarks.

Evidence

The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. This is the 2020 ViT preprint, later published at ICLR 2021; results depend on large-scale pretraining and studied recognition benchmarks.

Contributors

• The named authors listed in the linked research record · SCIENCE: Complete source byline retained in the research record; human research direction, method development and evaluation. Individual labor shares are not measured.

• Dosovitskiy and colleagues: Vision Transformer image-patch classification — original paper
• Dosovitskiy and colleagues: Vision Transformer image-patch classification — official research page

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