Method evidence record
Vision Transformer
The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs).
Source record
Citations copied verbatim from the method’s source record. No claim-level verification is inferred from them.
Vision Transformer (ViT)
Taxonomic method record · ml-model / deep-learning
- Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. · URL
- Touvron, H. et al. (2021). Training Data-Efficient Image Transformers. ICML. · URL
Curated claims
Claims persisted in the evidence ledger, each with its own assessment.
No curated claims yet
This view does not invent a claim assessment when the ledger has none.
Related methods
Generated from the method graph and shown as machine-suggested relations — no evidence claim is inferred.