MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation

TL;DR

MLNet introduces a mutual learning approach with neighborhood invariance to improve universal domain adaptation by reducing intra-domain variations and enhancing unknown-class identification, achieving state-of-the-art results.

Contribution

The paper proposes a novel Mutual Learning Network with neighborhood invariance that addresses intra-domain variation and unknown-class separation in UniDA.

Findings

Achieves superior performance on three benchmarks.

Outperforms existing methods in most settings.

Significantly improves unknown-class detection.

Abstract

Universal domain adaptation (UniDA) is a practical but challenging problem, in which information about the relation between the source and the target domains is not given for knowledge transfer. Existing UniDA methods may suffer from the problems of overlooking intra-domain variations in the target domain and difficulty in separating between the similar known and unknown class. To address these issues, we propose a novel Mutual Learning Network (MLNet) with neighborhood invariance for UniDA. In our method, confidence-guided invariant feature learning with self-adaptive neighbor selection is designed to reduce the intra-domain variations for more generalizable feature representation. By using the cross-domain mixup scheme for better unknown-class identification, the proposed method compensates for the misidentified known-class errors by mutual learning between the closed-set and open-set classifiers. Extensive experiments on three publicly available benchmarks demonstrate that our method achieves the best results compared to the state-of-the-arts in most cases and significantly outperforms the baseline across all the four settings in UniDA. Code is available at https://github.com/YanzuoLu/MLNet.