BDC-FR: Faster R-CNN with Balanced Domain Classifier for Cross-Domain Object Detection (S)
Shouhong Wan, Rui Wang, Peiquan Jin, Xuebin Yang · Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering · 2023
Object detectors trained with massive labeled data often suffer performance degradation in some particular scenarios with data distribution gap.Domain classifier is a commonly used method in the existing domain adaptation algorithms to alleviate the domain discrepancy.However, it has problems of instability in training, difficulty in obtaining optimal solutions and converging to an equilibrium point.To tackle this issue, we propose a novel balanced domain classifier (BDC), which not only eliminates domain discrepancy but also makes the domain classifier and the feature extractor maintain equilibrium during the adversarial learning.Furthermore, we propose an appropriate learning rate adjustment strategy, which makes the detection model converge to an equilibrium point more stably and more rapidly.Based on the domain-invariant region proposal network, we propose a cross-domain object detection model called Faster R-CNN with Balanced Domain Classifier (BDC-FR).The experimental results show that BDC-FR can effectively improve the performance of the cross-domain object detection model.