Verified65% confidenceFactTime unknown

2020年Google提出的ViT（Vision Transformer）证明将图像切分为16×16小块后，Transformer在图像分类任务上可以达到甚至超越CNN的性能

3

Sources

65%

Confidence

Long-term

Relevance

6/1/2026

First Seen

Sources

Hugging Face Transformers深度解析：16万Star的AI开源框架为何成为行业标配

githubhuggingface

Related Entities

ViTmodel Googlecompany CNNconcept

Related Claims

VerifiedVision Transformer（ViT）由Google在2020年提出，将图像分割为固定大小的patch作为序列输入Transformer编码器85% similar UnverifiedVision Transformer将图像切分为16×16的patch作为基本处理单元78% similar VerifiedVision Transformer（ViT）由Google Brain团队于2020年提出，将Transformer架构引入计算机视觉领域76% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/33026

API

curl https://kongchang.com/api/v1/knowledge/claims/33026

MCP

get_claim(id=33026)