Attention-based Domain Adaptation for Single Stage Detectors

While domain adaptation has been used to improve the performance of object detectors when the training and test data follow different distributions, previous work has mostly focused on two-stage detectors. This is because their use of region proposals makes it possible to perform local adaptation, which has been shown to significantly improve the adaptation effectiveness. Here, by contrast, we target single-stage architectures, which are better suited to resource-constrained detection than two-stage ones but do not provide region proposals. To nonetheless benefit from the strength of local adaptation, we introduce an attention mechanism that lets us identify the important regions on which adaptation should focus. Our approach is generic and can be integrated into any single-stage detector. We demonstrate this on standard benchmark datasets by applying it to both SSD and YOLO. Furthermore, for an equivalent single-stage architecture, our method outperforms the state-of-the-art domain adaptation technique even though it was designed specifically for this particular detector.