A Robust Negative Learning Approach to Partial Domain Adaptation Using Source Prototypes
This work addresses domain adaptation challenges for scenarios where source and target domains have mismatched label sets, offering incremental improvements in robustness and generalization.
The paper tackles the negative transfer problem in Partial Domain Adaptation by proposing a framework that uses source prototypes and robust target supervision to improve pseudo-label refinement and distribution alignment, achieving superior performance over state-of-the-art methods on benchmark datasets.
This work proposes a robust Partial Domain Adaptation (PDA) framework that mitigates the negative transfer problem by incorporating a robust target-supervision strategy. It leverages ensemble learning and includes diverse, complementary label feedback, alleviating the effect of incorrect feedback and promoting pseudo-label refinement. Rather than relying exclusively on first-order moments for distribution alignment, our approach offers explicit objectives to optimize intra-class compactness and inter-class separation with the inferred source prototypes and highly-confident target samples in a domain-invariant fashion. Notably, we ensure source data privacy by eliminating the need to access the source data during the adaptation phase through a priori inference of source prototypes. We conducted a series of comprehensive experiments, including an ablation analysis, covering a range of partial domain adaptation tasks. Comprehensive evaluations on benchmark datasets corroborate our framework's enhanced robustness and generalization, demonstrating its superiority over existing state-of-the-art PDA approaches.