search

Westlake-AI / openmixup

CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark
https://openmixup.readthedocs.io
Apache License 2.0
627 stars 62 forks source link

Update New Features and Update Documents in V0.2.6 #25

Closed Lupin1998 closed 2 years ago

Lupin1998 commented 2 years ago

Updating features:

  1. Support new self-supervised method BEiT with ViT-Base on ImageNet-1K, and fix bugs of CAE, MaskFeat, and SimMIM in Dataset, Model, and Head. Note that we added HOG feature implementation borrowed from the original repo for MaskFeat.
  2. Support new backbone architecture DeiT-3 and provide configs.
  3. Update pre-training and fine-tuning config files, and documents for the relevant masked image modeling (MIM) methods (BEiT, MaskFeat, CAE, and A2MIM).
  4. Support Grad-CAM visualization tools vis_cam.py of supported architectures.

Updating documents:

  1. Update the template and add the latest paper lists of mixup and MIM methods in Awesome Mixups and Awesome MIM.
  2. Update documents of tools.
Lupin1998 commented 2 years ago

Fixed bugs and updated features for MIM methods in OpenMixup V0.2.6.

Lupin1998 commented 2 years ago

Update new features and documents for OpenMixup V0.2.6 (issue #24).