Open Compound Domain Adaptation

Abstract

Figure 1: Open compound domain adaptation vs. traditional domain adaptation problems. (a) Unsupervised domain adaptation considers a single target domain whose examples are unlabeled and yet can be used during training. (b) Some works aim to generalize a model across various domains by learning from multiple discrete domains. (c) In this work, we do not assume any clear boundaries between domains. The compound target domain mixes different major factors underlying the data and can be seen as a combination of multiple traditional target domains. Moreover, open domains which are unseen in training could challenge the model at the inference stage.

Hardmix: A Regularization Method to Mitigate the Large Shift in Few-Shot Domain Adaptation

“…The classification accuracy in Table 1 is reported after 100 epochs of training. The state-of-the-art methods we used as comparison in supervised setting(S) are CCSA [2], d-SNE [7] and FADA [8], we also include several state-ofthe-art unsupervised methods(U) [5,6,4] for comparison. Cross-entropy (CE) classification for source and target data are also compared as a baseline.…”

“…The typical solution is to use another available dataset on a closely related task, which leads to the problem of domain adaptation [1]. Existing domain adaptation methods can be supervised [2], semi-supervised [3] or unsupervised [4,5,6]. The main task is to learn the knowledge from the source domain, which is adapted to the target domain.…”

Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation

“…A major class of adaptation approaches, including [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50], involves adversarial confusion or feature alignment between domains. The general concept of curriculum learning has been successfully applied to domain adaptation by ordering tasks [51], target-domain pixels [52], or domains [10], [11], [35], [53]. Our method belongs to the last group.…”

Knowledge Sharing via Domain Adaptation in Customs Fraud Detection

“…Representative techniques include latent distribution alignment between the source and target domains (Tzeng et al 2017;Hoffman et al 2018;Long et al 2017). Contrastive learning is used to extract discriminative features between classes (Kang et al 2019;Thota and Leontidis 2021), and the memory module is used to augment target features using incremental information (Asghar et al 2020;Zheng and Yang 2019;Liu et al 2020). A long-standing problem in domain adaptation is negative transfer, which refers to the abnormal scenarios when the source domain data causes reduced learning performance in the target domain due to a large discrepancy in data distributions (Wang et al 2019;Zhang et al 2020).…”