MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation
This addresses a practical challenge in domain adaptation for machine learning applications, but it is incremental as it builds on existing UniDA methods.
The paper tackles the problem of universal domain adaptation (UniDA), where source-target domain relations are unknown, by proposing MLNet with neighborhood invariance to reduce intra-domain variations and improve unknown-class identification, achieving state-of-the-art results on three benchmarks.
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.