type
status
date
slug
summary
tags
category
icon
password
Property
Aug 5, 2022 02:03 AM
URL
论文笔记的readpaper链接整理
Classic
Transformer系列
VIT: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
(mention page即可)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
MAE: Masked Autoencoders Are Scalable Vision Learners
DETR: End-to-End Object Detection with Transformers
深度预测
2019
fastdepth
2020
MiDaS
2021
DPT
进度表
PaperLib
