Domain Adaptive YOLO for One-Stage Cross-Domain Detection
This addresses domain adaptation for one-stage detectors, which are preferred in industrial applications due to speed, but it is incremental as it builds on existing domain adaptation techniques.
The paper tackled the problem of domain shift in object detection by proposing Domain Adaptive YOLO (DA-YOLO) to improve cross-domain performance for one-stage detectors, achieving significant improvements in tests on datasets like Cityscapes, KITTI, and SIM10K.
Domain shift is a major challenge for object detectors to generalize well to real world applications. Emerging techniques of domain adaptation for two-stage detectors help to tackle this problem. However, two-stage detectors are not the first choice for industrial applications due to its long time consumption. In this paper, a novel Domain Adaptive YOLO (DA-YOLO) is proposed to improve cross-domain performance for one-stage detectors. Image level features alignment is used to strictly match for local features like texture, and loosely match for global features like illumination. Multi-scale instance level features alignment is presented to reduce instance domain shift effectively , such as variations in object appearance and viewpoint. A consensus regularization to these domain classifiers is employed to help the network generate domain-invariant detections. We evaluate our proposed method on popular datasets like Cityscapes, KITTI, SIM10K and etc.. The results demonstrate significant improvement when tested under different cross-domain scenarios.