Multiple Subspace Alignment Improves Domain Adaptation

TL;DR

This paper introduces a new unsupervised domain adaptation method that aligns multiple low-dimensional subspaces on the Grassmann manifold to improve cross-domain visual recognition performance.

Contribution

It proposes representing datasets with multiple subspaces and aligning them on the Grassmann manifold, advancing beyond single subspace approaches in domain adaptation.

Findings

Achieves state-of-the-art results on benchmark datasets

Demonstrates superior performance over existing subspace methods

Validates effectiveness through extensive empirical studies

Abstract

We present a novel unsupervised domain adaptation (DA) method for cross-domain visual recognition. Though subspace methods have found success in DA, their performance is often limited due to the assumption of approximating an entire dataset using a single low-dimensional subspace. Instead, we develop a method to effectively represent the source and target datasets via a collection of low-dimensional subspaces, and subsequently align them by exploiting the natural geometry of the space of subspaces, on the Grassmann manifold. We demonstrate the effectiveness of this approach, using empirical studies on two widely used benchmarks, with state of the art domain adaptation performance