SSDA-YOLO: Semi-supervised Domain Adaptive YOLO for Cross-Domain Object Detection

TL;DR

This paper introduces SSDA-YOLO, a semi-supervised domain adaptive object detection method that combines YOLOv5 with domain adaptation techniques to improve cross-domain detection performance efficiently.

Contribution

It proposes a novel semi-supervised domain adaptive YOLO framework integrating knowledge distillation, scene style transfer, and consistency loss for better cross-domain detection.

Findings

Significant performance improvements on benchmarks like PascalVOC and Cityscapes.

Effective adaptation with a one-stage detector, suitable for industrial applications.

Demonstrated generalization on classroom yawning detection datasets.

Abstract

Domain adaptive object detection (DAOD) aims to alleviate transfer performance degradation caused by the cross-domain discrepancy. However, most existing DAOD methods are dominated by outdated and computationally intensive two-stage Faster R-CNN, which is not the first choice for industrial applications. In this paper, we propose a novel semi-supervised domain adaptive YOLO (SSDA-YOLO) based method to improve cross-domain detection performance by integrating the compact one-stage stronger detector YOLOv5 with domain adaptation. Specifically, we adapt the knowledge distillation framework with the Mean Teacher model to assist the student model in obtaining instance-level features of the unlabeled target domain. We also utilize the scene style transfer to cross-generate pseudo images in different domains for remedying image-level differences. In addition, an intuitive consistency loss is proposed to further align cross-domain predictions. We evaluate SSDA-YOLO on public benchmarks including PascalVOC, Clipart1k, Cityscapes, and Foggy Cityscapes. Moreover, to verify its generalization, we conduct experiments on yawning detection datasets collected from various real classrooms. The results show considerable improvements of our method in these DAOD tasks, which reveals both the effectiveness of proposed adaptive modules and the urgency of applying more advanced detectors in DAOD. Our code is available on \url{https://github.com/hnuzhy/SSDA-YOLO}.