Domain-Invariant Feature Alignment Using Variational Inference For Partial Domain Adaptation
This work addresses a practical problem in domain adaptation for machine learning practitioners, but it is incremental as it builds on existing techniques.
The paper tackles partial domain adaptation, where the source label set includes the target label set, by addressing issues like irrelevant source samples degrading performance. The proposed method combines variational inference, adversarial learning, and pseudo-labeling to achieve superior or comparable accuracy in cross-domain classification tasks.
The standard closed-set domain adaptation approaches seek to mitigate distribution discrepancies between two domains under the constraint of both sharing identical label sets. However, in realistic scenarios, finding an optimal source domain with identical label space is a challenging task. Partial domain adaptation alleviates this problem of procuring a labeled dataset with identical label space assumptions and addresses a more practical scenario where the source label set subsumes the target label set. This, however, presents a few additional obstacles during adaptation. Samples with categories private to the source domain thwart relevant knowledge transfer and degrade model performance. In this work, we try to address these issues by coupling variational information and adversarial learning with a pseudo-labeling technique to enforce class distribution alignment and minimize the transfer of superfluous information from the source samples. The experimental findings in numerous cross-domain classification tasks demonstrate that the proposed technique delivers superior and comparable accuracy to existing methods.