# Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning Source: [Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:59:51.007Z Authors: Hui Wang, Jian Tian, Songyuan Li, Hanbin Zhao, Qi Tian, Fei Wu, Xi Li Published: 2021-03-04T03:12:54.000Z ## Abstract Unsupervised domain adaptation (UDA) typically carries out knowledge transfer from a label-rich source domain to an unlabeled target domain by adversarial learning. In principle, existing UDA approaches mainly focus on the global distribution alignment between domains while ignoring the intrinsic local distribution properties. Motivated by this observation, we propose an end-to-end structure-conditioned adversarial learning scheme (SCAL) that is able to preserve the intra-class compactness during domain distribution alignment. By using local structures as structure-aware conditions, the proposed scheme is implemented in a structure-conditioned adversarial learning pipeline. The above learning procedure is iteratively performed by alternating between local structures establishment and structure-conditioned adversarial learning. Experimental results demonstrate the effectiveness of the proposed scheme in UDA scenarios. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()