Abstarct

We consider transferability estimation, the problem of estimating how well deep learning models transfer from a source to a target task. We focus on regression tasks, which received little previous attention, and propose two simple and computationally efficient approaches that estimate transferability based on the negative regularized mean squared error of a linear regression model. We prove novel theoretical results connecting our approaches to the actual transferability of the optimal target models obtained from the transfer learning process. Despite their simplicity, our approaches significantly outperform existing state-of-the-art regression transferability estimators in both accuracy and efficiency. On two large-scale keypoint regression benchmarks, our approaches yield 12% to 36% better results on average while being at least 27% faster than previous state-of-the-art methods.

PMLR page

Paper on PMLR

Supplementary material on PMLR

BibTex:

@inproceedings{Nguyen2023Simple,
  title={Simple Transferability Estimation for Regression Tasks},
  author={Cuong N. Nguyen and Phong Tran and Lam Si Tung Ho and Vu Dinh and Anh T. Tran and Tal Hassner and Cuong V. Nguyen},
  booktitle={The Conference on Uncertainty in Artificial Intelligence (UAI)},
  year={2023},
  url={https://talhassner.github.io/home/publication/2023_UAI}
}