Students Professional
JA EN

#vit

1 articles

01 ·VLMs & Multimodal·★ MEMBER·PAPER·7 min read Paper Deep Dive — ViT: Treating an Image Like a Sentence A reading of the ViT paper (Dosovitskiy et al., 2020/2021) grounded strictly in its own text: the move of treating 16x16 patches as words, what the position-embedding ablation actually showed, the price of dropping the convolutional inductive bias, and how conditional the claim 'beats CNNs at scale' really is.