Domain-Invariant Feature Alignment Using Variational Inference For Partial Domain Adaptation

TL;DR

This paper introduces a novel method combining variational inference, adversarial learning, and pseudo-labeling to improve partial domain adaptation by aligning class distributions and reducing source-only private information transfer.

Contribution

It proposes a new approach that effectively handles partial domain adaptation challenges by coupling variational information with adversarial learning and pseudo-labeling.

Findings

Achieves superior accuracy on multiple cross-domain tasks.

Effectively reduces transfer of source-private information.

Demonstrates robustness in partial domain adaptation scenarios.

Abstract

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.