DDRN: DETR with dual refinement networks for autonomous vehicle object detection

Object detection is an essential part of autonomous driving perception, as its effectiveness directly affects subsequent decision making and control. However, the difficulty of detecting small objects and the complexity of the driving environment poses challenges that prevent existing detectors from fully meeting the safety and efficiency requirements of autonomous driving systems. To address these challenges, we propose three components: Feature Pyramid Network-α (FPN-α), Classification Refinement Networks (CRN), and Localization Refinement Networks (LRN), and organize them into DETR with Dual Refinement Networks (DDRN). FPN-α determines to what degree deep layers in FPN participate in the learning of shallow layers by reweighting during gradient back propagation, which addresses background misdetection in small object detection. CRN and LRN integrate FPN-α features with predictions from advanced end-to-end detectors to further optimize classification and localization, respectively. Compared to several advanced autonomous driving object detectors, our method achieved an improvement of 1.4% and 1.1% in average precision (AP) on two public autonomous driving datasets, respectively. Extensive experiments have demonstrated the effectiveness, robustness, and applicability of DDRN.