Improving Online Source-free Domain Adaptation for Object Detection by Unsupervised Data Acquisition
This addresses the challenge of effective object detection in diverse environments for autonomous vehicles, but it is incremental as it builds on existing O-SFDA methods.
The paper tackled the problem of improving object detection in autonomous vehicles by enhancing Online Source-Free Domain Adaptation (O-SFDA) through unsupervised data acquisition, resulting in a method that outperforms existing state-of-the-art O-SFDA techniques on a real-world dataset.
Effective object detection in autonomous vehicles is challenged by deployment in diverse and unfamiliar environments. Online Source-Free Domain Adaptation (O-SFDA) offers model adaptation using a stream of unlabeled data from a target domain in an online manner. However, not all captured frames contain information beneficial for adaptation, especially in the presence of redundant data and class imbalance issues. This paper introduces a novel approach to enhance O-SFDA for adaptive object detection through unsupervised data acquisition. Our methodology prioritizes the most informative unlabeled frames for inclusion in the online training process. Empirical evaluation on a real-world dataset reveals that our method outperforms existing state-of-the-art O-SFDA techniques, demonstrating the viability of unsupervised data acquisition for improving the adaptive object detector.