Progressive Domain Adaptation for Object Detection
This addresses the costly annotation issue for object detection by improving domain adaptation, but it is incremental as it builds on existing adversarial learning and translation techniques.
The paper tackles the problem of object detection models not generalizing well to different image distributions by proposing a progressive domain adaptation method that uses an intermediate domain to bridge large domain gaps, achieving favorable performance against state-of-the-art methods on the target domain.
Recent deep learning methods for object detection rely on a large amount of bounding box annotations. Collecting these annotations is laborious and costly, yet supervised models do not generalize well when testing on images from a different distribution. Domain adaptation provides a solution by adapting existing labels to the target testing data. However, a large gap between domains could make adaptation a challenging task, which leads to unstable training processes and sub-optimal results. In this paper, we propose to bridge the domain gap with an intermediate domain and progressively solve easier adaptation subtasks. This intermediate domain is constructed by translating the source images to mimic the ones in the target domain. To tackle the domain-shift problem, we adopt adversarial learning to align distributions at the feature level. In addition, a weighted task loss is applied to deal with unbalanced image quality in the intermediate domain. Experimental results show that our method performs favorably against the state-of-the-art method in terms of the performance on the target domain.