Zero-shot domain adaptation based on dual-level mix and contrast
This addresses domain adaptation in scenarios with mismatched tasks, which is incremental as it builds on existing techniques to handle task bias.
The paper tackles the problem of zero-shot domain adaptation where domain-invariant features learned from an irrelevant task are biased for the task of interest, proposing a method with dual-level mixups, extended adversarial learning, and contrastive learning to reduce task bias. Experimental results show it achieves good performance on several benchmarks.
Zero-shot domain adaptation (ZSDA) is a domain adaptation problem in the situation that labeled samples for a target task (task of interest) are only available from the source domain at training time, but for a task different from the task of interest (irrelevant task), labeled samples are available from both source and target domains. In this situation, classical domain adaptation techniques can only learn domain-invariant features in the irrelevant task. However, due to the difference in sample distribution between the two tasks, domain-invariant features learned in the irrelevant task are biased and not necessarily domain-invariant in the task of interest. To solve this problem, this paper proposes a new ZSDA method to learn domain-invariant features with low task bias. To this end, we propose (1) data augmentation with dual-level mixups in both task and domain to fill the absence of target task-of-interest data, (2) an extension of domain adversarial learning to learn domain-invariant features with less task bias, and (3) a new dual-level contrastive learning method that enhances domain-invariance and less task biasedness of features. Experimental results show that our proposal achieves good performance on several benchmarks.