LA-SSL

January 15, 2025 ยท View on GitHub

Code for paper Making Self-supervised Learning Robust to Spurious Correlation via Learning-speed Aware Sampling


Requirements

  • cudatoolkit=10.2
  • matplotlib==3.4.3
  • numpy==1.21.4
  • pandas==1.3.4
  • scikit-learn==1.0.1
  • torch==1.10.0
  • torchvision==0.11.1
  • tqdm=4.64.0