Skip to content

Latest commit

 

History

History
7 lines (4 loc) · 274 Bytes

220429 Vision-Language Pre-Training for Boosting Scene Text Detectors.md

File metadata and controls

7 lines (4 loc) · 274 Bytes

https://arxiv.org/abs/2204.13867

Vision-Language Pre-Training for Boosting Scene Text Detectors (Sibo Song, Jianqiang Wan, Zhibo Yang, Jun Tang, Wenqing Cheng, Xiang Bai, Cong Yao)

잠깐 이야기가 나왔었던 clip 스타일 프리트레이닝이네요.

#pretraining