Skip to content

This repository is a collection of awesome things about robust finetuning, including papers, code, etc.

License

Notifications You must be signed in to change notification settings

LixDemon/Awesome-Robust-Finetuning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 

Repository files navigation

Awesome-Robust-Finetuning

Awesome

This repository is a collection of awesome things about Robust Finetuning, including papers, code, etc.

If you would like to contribute to our repository or have any questions/advice, see Contributing & Contact.

Contents

Papers

We list papers and the implementation code.

  • Robust fine-tuning of zero-shot models [CVPR 2022] [Code]
  • Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution [ICLR 2022]
  • Finetune Like You Pretrain: Improved Finetuning of Zero-Shot Vision Models [CVPR 2023] [Code]
  • Masked Images Are Counterfactual Samples for Robust Fine-Tuning [CVPR 2023] [Code]
  • Trainable Projected Gradient Method for Robust Fine-tuning [CVPR 2023] [Code]
  • Fast Trainable Projection for Robust Fine-Tuning [NeurIPS 2023] [Code]
  • Geodesic Multi-Modal Mixup for Robust Fine-Tuning [NeurIPS 2023] [Code]
  • Towards Calibrated Robust Fine-Tuning of Vision-Language Models [NeurIPS 2023] [Code]
  • Context-Aware Robust Fine-Tuning [IJCV 2023]
  • AutoFT: Robust Fine-Tuning by Optimizing Hyperparameters on OOD Data [arXiv 2024]
  • Anchor-based Robust Finetuning of Vision-Language Models [CVPR 2024]
  • Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance [ICLR 2024]

Contributing & Contact

Feel free to contribute to our repository.

  • If you woulk like to correct mistakes, please do it directly;
  • If you would like to add/update papers, please follow the existing format;
  • If you have any questions or advice, please contact us by email ([email protected]) or GitHub issues.

Thank you for your support!

About

This repository is a collection of awesome things about robust finetuning, including papers, code, etc.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published