researchmm/soho
[CVPR'21 Oral] Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning
Python
Issues
- 4
- 1
The Accuracy of Masked Visual Modeling
#10 opened by mhyeh - 0
你们这是开源了个寂寞啊。。
#13 opened by Sry2016 - 0
pretrain model of soho based on resenet101
#12 opened by maogewudi007 - 0
It is abnormal , so many unexpected keys???
#11 opened by alice-cool - 0
- 0
- 0
- 0
Presentation slide
#4 opened by pqviet - 2
No module named 'SOHO.version'
#6 opened by grandsmile - 1
pretrained models can not be downloaded
#5 opened by kaizhigaosu - 0
Do you plan to release the training configurations and scripts of the pre-training?
#2 opened by Jxu-Thu - 1
Where I can find the VD?
#1 opened by LIUYUANWEI98