Robust Class-Conditional Distribution Alignment for Partial Domain Adaptation
This work addresses partial domain adaptation for machine learning practitioners, but it appears incremental as it builds on existing methods with specific improvements.
The paper tackles the problem of negative transfer in partial domain adaptation by addressing unwanted source categories and inadequate class-level alignment, resulting in superior performance compared to benchmarks as demonstrated in experiments.
Unwanted samples from private source categories in the learning objective of a partial domain adaptation setup can lead to negative transfer and reduce classification performance. Existing methods, such as re-weighting or aggregating target predictions, are vulnerable to this issue, especially during initial training stages, and do not adequately address class-level feature alignment. Our proposed approach seeks to overcome these limitations by delving deeper than just the first-order moments to derive distinct and compact categorical distributions. We employ objectives that optimize the intra and inter-class distributions in a domain-invariant fashion and design a robust pseudo-labeling for efficient target supervision. Our approach incorporates a complement entropy objective module to reduce classification uncertainty and flatten incorrect category predictions. The experimental findings and ablation analysis of the proposed modules demonstrate the superior performance of our proposed model compared to benchmarks.