Grassmannian Graph-attentional Landmark Selection for Domain Adaptation

TL;DR

This paper introduces a novel Grassmannian graph-attentional landmark selection framework that enhances domain adaptation by combining sample hierarchy and geometric properties, leading to improved classification accuracy.

Contribution

It proposes a new GGLS framework that integrates attention-based landmark selection with Grassmannian distribution and knowledge adaptation for robust domain adaptation.

Findings

Outperforms state-of-the-art methods in cross-domain visual recognition.

Effectively leverages hierarchical sample relationships and geometric properties.

Achieves better classification accuracy across multiple real-world tasks.

Abstract

Domain adaptation aims to leverage information from the source domain to improve the classification performance in the target domain. It mainly utilizes two schemes: sample reweighting and feature matching. While the first scheme allocates different weights to individual samples, the second scheme matches the feature of two domains using global structural statistics. The two schemes are complementary with each other, which are expected to jointly work for robust domain adaptation. Several methods combine the two schemes, but the underlying relationship of samples is insufficiently analyzed due to the neglect of the hierarchy of samples and the geometric properties between samples. To better combine the advantages of the two schemes, we propose a Grassmannian graph-attentional landmark selection (GGLS) framework for domain adaptation. GGLS presents a landmark selection scheme using attention-induced neighbors of the graphical structure of samples and performs distribution adaptation and knowledge adaptation over Grassmann manifold. the former treats the landmarks of each sample differently, and the latter avoids feature distortion and achieves better geometric properties. Experimental results on different real-world cross-domain visual recognition tasks demonstrate that GGLS provides better classification accuracies compared with state-of-the-art domain adaptation methods.