Joint Attention-Driven Domain Fusion and Noise-Tolerant Learning for Multi-Source Domain Adaptation
This work addresses domain adaptation challenges for machine learning applications where labeled data is scarce, though it appears incremental as it builds on existing methods to improve robustness.
The paper tackles performance bottlenecks in multi-source unsupervised domain adaptation caused by domain discrepancies and noisy pseudo-labels, proposing an attention-driven domain fusion and noise-tolerant learning approach that achieves superior state-of-the-art results on benchmarks.
As a study on the efficient usage of data, Multi-source Unsupervised Domain Adaptation transfers knowledge from multiple source domains with labeled data to an unlabeled target domain. However, the distribution discrepancy between different domains and the noisy pseudo-labels in the target domain both lead to performance bottlenecks of the Multi-source Unsupervised Domain Adaptation methods. In light of this, we propose an approach that integrates Attention-driven Domain fusion and Noise-Tolerant learning (ADNT) to address the two issues mentioned above. Firstly, we establish a contrary attention structure to perform message passing between features and to induce domain movement. Through this approach, the discriminability of the features can also be significantly improved while the domain discrepancy is reduced. Secondly, based on the characteristics of the unsupervised domain adaptation training, we design an Adaptive Reverse Cross Entropy loss, which can directly impose constraints on the generation of pseudo-labels. Finally, combining these two approaches, experimental results on several benchmarks further validate the effectiveness of our proposed ADNT and demonstrate superior performance over the state-of-the-art methods.