Unsupervised domain adaptation aims to learn a task classifier that performs well on the unlabeled target domain, by utilizing labeled source domain. Inspiring results have been acquired learning domain-invariant deep features via domain-adversarial training. However, its parallel design of and classifiers limits ability achieve finer category-level alignment. To promote categorical (CatDA), ba...

Domain alignment (DA) has been widely used in unsupervised domain adaptation. Many existing DA methods assume that a low source risk, together with the of distributions and target, means target risk. In this paper, we show does not always hold. We thus propose novel metric-learning-assisted adaptation (MLA-DA) method, which employs triplet loss for helping better feature alignment. explore rela...

Domain adaptation assumes that samples from source and target domains are freely accessible during a training phase. However, such an assumption is rarely plausible in the real world possibly causes data privacy issues, especially when label of domain can be sensitive attribute as identifier. To avoid accessing could contain information, we introduce free (SFDA). Our key idea to leverage pretra...

Batch normalization (BN) is widely used in modern deep neural networks, which has been shown to represent the domain-related knowledge, and thus ineffective for cross-domain tasks like unsupervised domain adaptation (UDA). Existing BN variant methods aggregate source target knowledge same channel module. However, misalignment between features of corresponding channels across domains often leads...

Collection of real world annotations for training semantic segmentation models is an expensive process. Unsupervised domain adaptation (UDA) tries to solve this problem by studying how more accessible data such as synthetic can be used train and adapt images without requiring their annotations. Recent UDA methods applies self-learning on pixel-wise classification loss using a student teacher ne...

Transfer learning (TL), a crucial subfield of machine learning, aims to accomplish task in the target domain with acquired knowledge source domain. Specifically, effective adaptation (DA) facilitates delivery TL where all data samples two domains are distributed same feature space. In this paper, quantum implementations DA classifier presented speedup compared classical classifier. One implemen...