Kernel Alignment for Unsupervised Transfer Learning

TL;DR

This paper introduces a kernel alignment method for unsupervised transfer learning that iteratively minimizes distribution differences, demonstrating improved performance on benchmark datasets.

Contribution

It proposes a simple, intuitive kernel alignment approach for transfer learning, connecting it to HSIC and QMI, and shows its effectiveness on vision benchmarks.

Findings

Outperforms some state-of-the-art transfer learning methods.

Effectively minimizes distribution differences between source and target.

Applicable to computer vision datasets.

Abstract

The ability of a human being to extrapolate previously gained knowledge to other domains inspired a new family of methods in machine learning called transfer learning. Transfer learning is often based on the assumption that objects in both target and source domains share some common feature and/or data space. In this paper, we propose a simple and intuitive approach that minimizes iteratively the distance between source and target task distributions by optimizing the kernel target alignment (KTA). We show that this procedure is suitable for transfer learning by relating it to Hilbert-Schmidt Independence Criterion (HSIC) and Quadratic Mutual Information (QMI) maximization. We run our method on benchmark computer vision data sets and show that it can outperform some state-of-art methods.