A Brief Review of Domain Adaptation

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in real-world applications where fall different distributions, due many factors, e.g., collecting sources or having an outdated set change of over time.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 discrepancy across domain naively applying trained new dataset cause degradation performance. Domain adaptation subfield within aims cope with these types problems by aligning disparity between domains such can generalized into interest. This paper focuses unsupervised adaptation, labels are only available source domain. It addresses categorization viewpoints. Besides, it presents some successful shallow deep approaches aim deal problems.