Deep Domain Adaptive Object Detection: a Survey
This is a survey paper that organizes existing research for practitioners and researchers in computer vision, but it presents no new methods or results.
This paper surveys deep domain adaptive object detection (DDAOD) methods, which address the challenge of training object detectors when labeled data is scarce or training/test distributions differ, by reviewing state-of-the-art approaches and categorizing them into five groups.
Deep learning (DL) based object detection has achieved great progress. These methods typically assume that large amount of labeled training data is available, and training and test data are drawn from an identical distribution. However, the two assumptions are not always hold in practice. Deep domain adaptive object detection (DDAOD) has emerged as a new learning paradigm to address the above mentioned challenges. This paper aims to review the state-of-the-art progress on deep domain adaptive object detection approaches. Firstly, we introduce briefly the basic concepts of deep domain adaptation. Secondly, the deep domain adaptive detectors are classified into five categories and detailed descriptions of representative methods in each category are provided. Finally, insights for future research trend are presented.