Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation

TL;DR

This paper introduces a novel universal domain adaptation framework that leverages inter-sample affinity and knowability-based labeling to improve the distinction between known and unknown samples, significantly enhancing performance.

Contribution

The paper proposes a new UDA method exploiting inter-sample affinity and a knowability-guided labeling scheme for better unknown sample detection.

Findings

Outperforms state-of-the-art methods on four datasets

Effectively distinguishes known and unknown samples

Reduces inter-sample affinity between unknown and known samples

Abstract

Universal domain adaptation (UniDA) aims to transfer the knowledge of common classes from the source domain to the target domain without any prior knowledge on the label set, which requires distinguishing in the target domain the unknown samples from the known ones. Recent methods usually focused on categorizing a target sample into one of the source classes rather than distinguishing known and unknown samples, which ignores the inter-sample affinity between known and unknown samples and may lead to suboptimal performance. Aiming at this issue, we propose a novel UDA framework where such inter-sample affinity is exploited. Specifically, we introduce a knowability-based labeling scheme which can be divided into two steps: 1) Knowability-guided detection of known and unknown samples based on the intrinsic structure of the neighborhoods of samples, where we leverage the first singular vectors of the affinity matrices to obtain the knowability of every target sample. 2) Label refinement based on neighborhood consistency to relabel the target samples, where we refine the labels of each target sample based on its neighborhood consistency of predictions. Then, auxiliary losses based on the two steps are used to reduce the inter-sample affinity between the unknown and the known target samples. Finally, experiments on four public datasets demonstrate that our method significantly outperforms existing state-of-the-art methods.