MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation
DOI:
https://doi.org/10.1609/aaai.v38i4.28182Keywords:
CV: Object Detection & Categorization, ML: Transfer, Domain Adaptation, Multi-Task LearningAbstract
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.Downloads
Published
2024-03-24
How to Cite
Lu, Y., Shen, M., Ma, A. J., Xie, X., & Lai, J.-H. (2024). MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(4), 3900-3908. https://doi.org/10.1609/aaai.v38i4.28182
Issue
Section
AAAI Technical Track on Computer Vision III