Simple Transferability Estimation for Regression Tasks

TL;DR

This paper introduces two simple, efficient methods for estimating transferability in regression tasks, demonstrating significant improvements over existing estimators in accuracy and speed on large-scale benchmarks.

Contribution

It proposes novel transferability estimation approaches for regression tasks, with theoretical justifications and superior empirical performance.

Findings

12% to 36% better results on benchmarks

At least 27% faster than previous methods

Significant accuracy improvements over state-of-the-art

Abstract

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.