swin transformer backbone for qpic

hitachi-rd-cv / qpic

Repo for CVPR2021 paper "QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information"

Apache License 2.0

131 stars 33 forks source link

Open SISTMrL opened 3 years ago

SISTMrL commented 3 years ago

hi, have you tried to replace resnet with swin transformer, could you give me some suggestions, thanks.

hutuo1213 commented 1 year ago

Did you implement the QPIC with Swin-Tiny program? I use its training and its mAP value is always 0, can you give me some advice. Thank you!