Many domain adaptation approaches rely on learning cross domain shared representations to transfer the knowledge learned in one domain to other domains. Traditional domain adaptation only considers adapting for one task. In this paper, we explore multi-task representation learning under the domain adaptation scenario. We propose a neural network framework that supports domain adaptation for mul...

Classical machine learning assumes that the training and test sets come from same distributions. Therefore, a model learned labeled data is expected to perform well on data. However, this assumption may not always hold in real-world applications where fall different distributions, due many factors, e.g., collecting sources or having an outdated set change of over time. In case, there would be d...

Domain Adaption tasks have recently attracted substantial attention in computer vision as they improve the transferability of deep network models from a source to target domain with different characteristics. A large body state-of-the-art domain-adaptation methods was developed for image classification purposes, which may be inadequate segmentation tasks. We propose adapt networks constrained f...

Domain adaptation (DA) aims to transfer knowledge from a label-rich and related domain (source domain) label-scare (target domain). Pseudo-labeling has recently been widely explored used in DA. However, this line of research is still confined the inaccuracy pseudo labels. In paper, we explore imbalance issue performance among classes in-depth observe that worse performances all are likely furth...

The gap in data distribution motivates domain adaptation research. In this area, image classification intrinsically requires the source and target features to be co-located if they are of same class. However, many works only take a global view gap. That is, make distributions globally overlap; does not necessarily lead feature co-location at class level. To resolve problem, we study metric lear...

This paper studies the problem of unsupervised domain adaption in universal scenario, which only some classes are shared between source and target domains. We present a scoring scheme that is effective identifying samples classes. The score used to select for apply specific losses during training; pseudo-labels high confidence regularization low samples. Taken together, our method shown outperf...