Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling
This addresses domain adaptation for classification tasks where labeled data is scarce in the target domain, representing an incremental improvement over existing pseudo-labeling methods.
The paper tackles the problem of inaccurate pseudo-labeling in unsupervised domain adaptation, which can lead to error accumulation, by proposing a selective pseudo-labeling strategy based on structured prediction that leverages clustering in the feature space. Experimental results show it outperforms state-of-the-art methods on four datasets.
Unsupervised domain adaptation aims to address the problem of classifying unlabeled samples from the target domain whilst labeled samples are only available from the source domain and the data distributions are different in these two domains. As a result, classifiers trained from labeled samples in the source domain suffer from significant performance drop when directly applied to the samples from the target domain. To address this issue, different approaches have been proposed to learn domain-invariant features or domain-specific classifiers. In either case, the lack of labeled samples in the target domain can be an issue which is usually overcome by pseudo-labeling. Inaccurate pseudo-labeling, however, could result in catastrophic error accumulation during learning. In this paper, we propose a novel selective pseudo-labeling strategy based on structured prediction. The idea of structured prediction is inspired by the fact that samples in the target domain are well clustered within the deep feature space so that unsupervised clustering analysis can be used to facilitate accurate pseudo-labeling. Experimental results on four datasets (i.e. Office-Caltech, Office31, ImageCLEF-DA and Office-Home) validate our approach outperforms contemporary state-of-the-art methods.