Joint Attention-Driven Domain Fusion and Noise-Tolerant Learning for Multi-Source Domain Adaptation

TL;DR

This paper introduces ADNT, a novel method for multi-source unsupervised domain adaptation that combines attention-driven domain fusion with noise-tolerant learning to improve feature discriminability and handle noisy pseudo-labels.

Contribution

It proposes a new framework integrating a contrary attention structure for domain fusion and an adaptive reverse cross entropy loss for noise-tolerant pseudo-labeling, advancing the state-of-the-art.

Findings

Achieves superior performance on multiple benchmarks.

Effectively reduces domain discrepancy and improves feature discriminability.

Demonstrates robustness to noisy pseudo-labels.

Abstract

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.