Simple Transferability Estimation for Regression Tasks

Cuong N. Nguyen, Phong Tran, Lam Si Tung Ho, Vu Dinh, Anh T. Tran, Tal Hassner, Cuong V. Nguyen

Research output: Contribution to journalConference articlepeer-review


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.

Original languageEnglish
Pages (from-to)1510-1521
Number of pages12
JournalProceedings of Machine Learning Research
StatePublished - 2023
Event39th Conference on Uncertainty in Artificial Intelligence, UAI 2023 - Pittsburgh, United States
Duration: 31 Jul 20234 Aug 2023

Bibliographical note

Publisher Copyright:
© UAI 2023. All rights reserved.


Dive into the research topics of 'Simple Transferability Estimation for Regression Tasks'. Together they form a unique fingerprint.

Cite this