CILP：Learning Transferable Visual Models From Natural Language Supervision

太棒了! 目前共计 241 篇日志。 继续努力。

2022

12-20

CILP：Learning Transferable Visual Models From Natural Language Supervision

12-11

Res2Net：A New Multi-scale Backbone Architecture

11-15

YOLOF：You Only Look One-level Feature

11-13

MAE：Masked Autoencoders Are Scalable Vision Learners

10-25

SVTR：Scene Text Recognition with a Single Visual Model

10-21

YOLOv5-nopaper

10-11

Swin Transformer：Hierarchical Vision Transformer using Shifted Windows

10-04

OAA：Online Attention Accumulation for Weakly Supervised Semantic Segmentation