Coupling Adversarial Learning with Selective Voting Strategy for Distribution Alignment in Partial Domain Adaptation
This work addresses partial domain adaptation, a realistic scenario in domain adaptation, with incremental improvements over existing methods.
The paper tackles partial domain adaptation where the source label set contains the target label set, addressing issues where irrelevant source categories hinder knowledge transfer. It proposes coupling adversarial learning with a selective voting strategy to align distributions, achieving superior or comparable accuracy in cross-domain classification tasks.
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.