Skip to content

Repository files navigation

Code for PatAug

Example code to run PatAug: Augmentation of Augmentation for Test-Time Adaptation (MM'25) with specialization benchmark.

Dataset preparation

  • Prepare the datasets following the guideline in CoOp under dataset root ./dataset_special/.

Environment

  • Run conda env create -f environment.yml to install necessary packages.

Run

  • Run bash pataug.sh to run TTA on all specialization datasets.
  • Check log in ./PatAug/

About

PyTorch implementation of PatAug: Augmentation of Augmentation for Test-Time Adaptation

Resources

Stars

3 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages