Coupling Adversarial Learning with Selective Voting Strategy for Distribution Alignment in Partial Domain Adaptation

TL;DR

This paper introduces a novel partial domain adaptation method that strategically selects target samples and combines adversarial learning with selective voting to improve distribution alignment and classification accuracy.

Contribution

It proposes a new mechanism for selecting confident target samples and couples class-discriminative feature learning with adversarial objectives for partial domain adaptation.

Findings

Achieves superior accuracy on multiple cross-domain tasks.

Effectively mitigates negative transfer from source-only samples.

Demonstrates robustness across various domain shifts.

Abstract

In contrast to a standard closed-set domain adaptation task, partial domain adaptation setup caters to a realistic scenario by relaxing the identical label set assumption. The fact of source label set subsuming the target label set, however, introduces few additional obstacles as training on private source category samples thwart relevant knowledge transfer and mislead the classification process. To mitigate these issues, we devise a mechanism for strategic selection of highly-confident target samples essential for the estimation of class-importance weights. Furthermore, we capture class-discriminative and domain-invariant features by coupling the process of achieving compact and distinct class distributions with an adversarial objective. Experimental findings over numerous cross-domain classification tasks demonstrate the potential of the proposed technique to deliver superior and comparable accuracy over existing methods.