Awesome

SHERL

PyTorch implementation for ECCV2024 paper of “SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning”.

It is built on top of the UniPT, LST, VSE-infty, CLIP-ViL, CLIP4Clip, MDETR and Awesome_Pretraining_Transfering.

If any problems, please contact me at r1228240468@gmail.com. (diaohw@mail.dlut.edu.cn is deprecated)

Coming soon! Sorry for the late release.