Few-Shot Domain Adaptation via Mixup Optimal Transport

• Published in: IEEE transactions on image processing 2022-01, Vol.31, p.2518-2528
• Main Authors: Xu, Bingrong, Zeng, Zhigang, Lian, Cheng, Ding, Zhengming
• Format: Article
• Language: English
• Subjects: Adaptation; Adaptation models; Automation; Classifiers; Couplings; data augmentation; Deep learning; domain adaptation; Domains; Eigenvectors; Feature extraction; Few-shot learning; Numerical models; optimal transport; Regularization; Training
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2022.3157139

Unsupervised domain adaptation aims to learn a classification model for the target domain without any labeled samples by transferring the knowledge from the source domain with sufficient labeled samples. The source and the target domains usually share the same label space but are with different data distributions. In this paper, we consider a more difficult but insufficient-explored problem named as few-shot domain adaptation, where a classifier should generalize well to the target domain given only a small number of examples in the source domain. In such a problem, we recast the link between the source and target samples by a mixup optimal transport model. The mixup mechanism is integrated into optimal transport to perform the few-shot adaptation by learning the cross-domain alignment matrix and domain-invariant classifier simultaneously to augment the source distribution and align the two probability distributions. Moreover, spectral shrinkage regularization is deployed to improve the transferability and discriminability of the mixup optimal transport model by utilizing all singular eigenvectors. Experiments conducted on several domain adaptation tasks demonstrate the effectiveness of our proposed model dealing with the few-shot domain adaptation problem compared with state-of-the-art methods.