Correlation-aware Adversarial Domain Adaptation and Generalization

29 Nov 2019  ·  Mohammad Mahfujur Rahman, Clinton Fookes, Mahsa Baktashmotlagh, Sridha Sridharan ·

Domain adaptation (DA) and domain generalization (DG) have emerged as a solution to the domain shift problem where the distribution of the source and target data is different. The task of DG is more challenging than DA as the target data is totally unseen during the training phase in DG scenarios. The current state-of-the-art employs adversarial techniques, however, these are rarely considered for the DG problem. Furthermore, these approaches do not consider correlation alignment which has been proven highly beneficial for minimizing domain discrepancy. In this paper, we propose a correlation-aware adversarial DA and DG framework where the features of the source and target data are minimized using correlation alignment along with adversarial learning. Incorporating the correlation alignment module along with adversarial learning helps to achieve a more domain agnostic model due to the improved ability to reduce domain discrepancy with unlabeled target data more effectively. Experiments on benchmark datasets serve as evidence that our proposed method yields improved state-of-the-art performance.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Domain Adaptation ImageCLEF-DA CAADA Accuracy 80.2 # 13
Domain Adaptation Office-31 CAADA Average Accuracy 78.3 # 27
Domain Adaptation Office-Home CAADA Accuracy 48.19 # 15
Domain Generalization PACS CAADG (Alexnet) Average Accuracy 71.98 # 79


No methods listed for this paper. Add relevant methods here