researchmm / soho

[CVPR'21 Oral] Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning
206 stars 19 forks source link

Where I can find the VD? #1

Open LIUYUANWEI98 opened 3 years ago

LIUYUANWEI98 commented 3 years ago

In the paper, there is a Visual Dictionary(VD) to remodel the image of query, but the class of SOHO_direct_VD(SOHO/models/necks/utils.py) only operate the image by torch.agrmax in the code, which is not matched with what you described in paper. Please tell me where I can find the VD which is the same as described in the paper. Thank you.

jeasinema commented 3 years ago

Seconding here. The current VD seems to be an identity mapping. How should I repro your result with the complete model? Thanks for the help.