Traffic-X / ViT-CoMer

Official implementation of the CVPR 2024 paper ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions.

Release of the pretrained weights on ImageNet-1K?

lqxisok opened this issue 5 months ago · comments

Lv Qingxuan commented 5 months ago

Can you release the pretrained weights on ImageNet-1K for Vit-CoMer (ViT small / base)?

clxia12 commented 4 months ago

Please refer to the link: https://github.com/Traffic-X/ViT-CoMer/blob/main/detection/README.md