Multi-component Image Translation for Deep Domain Generalization

21 Dec 2018  ·  Mohammad Mahfujur Rahman, Clinton Fookes, Mahsa Baktashmotlagh, Sridha Sridharan ·

Domain adaption (DA) and domain generalization (DG) are two closely related methods which are both concerned with the task of assigning labels to an unlabeled data set. The only dissimilarity between these approaches is that DA can access the target data during the training phase, while the target data is totally unseen during the training phase in DG. The task of DG is challenging as we have no earlier knowledge of the target samples. If DA methods are applied directly to DG by a simple exclusion of the target data from training, poor performance will result for a given task. In this paper, we tackle the domain generalization challenge in two ways. In our first approach, we propose a novel deep domain generalization architecture utilizing synthetic data generated by a Generative Adversarial Network (GAN). The discrepancy between the generated images and synthetic images is minimized using existing domain discrepancy metrics such as maximum mean discrepancy or correlation alignment. In our second approach, we introduce a protocol for applying DA methods to a DG scenario by excluding the target data from the training phase, splitting the source data to training and validation parts, and treating the validation data as target data for DA. We conduct extensive experiments on four cross-domain benchmark datasets. Experimental results signify our proposed model outperforms the current state-of-the-art methods for DG.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Domain Generalization PACS JAN-COMBO (Alexnet) Average Accuracy 69.45 # 89

Methods


No methods listed for this paper. Add relevant methods here