Most domain adaptation methods for machine reading comprehension (MRC) use a pre-trained question-answer (QA) construction model to generate pseudo QA pairs MRC transfer. Such process will inevitably introduce mismatched (i.e., Noisy Correspondence) due i) the unavailable in target documents, and ii) shift during applying domain. Undoubtedly, noisy correspondence degenerate performance of MRC, ...

Deep Neural Networks (DNNs) trained on one dataset (source domain) do not perform well another set of data (target domain), which is different but has similar properties as the source domain. Domain Adaptation (DA) strives to alleviate this problem and great potential in its application practical settings, real-world scenarios, industrial applications many domains. Various DA methods aimed at i...

Recent years have witnessed great progress in synthetic aperture radar (SAR) target detection methods based on deep learning. However, these generally assume the training data and test obey same distribution, which does not always hold when parameters, imaging algorithm, viewpoints, scenes, etc., change practice. When such a distribution mismatch occurs, it will cause significant performance dr...

Face anti-spoofing (FAS) approaches based on unsupervised domain adaption (UDA) have drawn growing attention due to promising performances for target scenarios. Most existing UDA FAS methods typically fit the trained models via aligning distribution of semantic high-level features. However, insufficient supervision unlabeled domains and neglect low-level feature alignment degrade methods. To ad...

Unsupervised domain adaptation addresses the problem of classifying data in an unlabeled target domain, given labeled source that share a common label space but follow different distribution. Most recent methods take approach explicitly aligning feature distributions between two domains. Differently, motivated by fundamental assumption for adaptability, we re-cast as discriminative clustering d...