Strengthening Small Object Detection in Adapted RT-DETR Through Robust Enhancements
Manav Madan, Christoph Reich
Abstract
RT-DETR (Real-Time DEtection TRansformer) has recently emerged as a promising model for object detection in images, yet its performance on small objects remains limited, particularly in terms of robustness. While various approaches have been explored, developing effective solutions for reliable small object detection remains a significant challenge. This paper introduces an adapted variant of RT-DETR, specifically designed to enhance robustness in small object detection. The model was first designed on one dataset and subsequently transferred to others to validate generalization. Key contributions include replacing components of the feed-forward neural network (FFNN) within a hybrid encoder with Hebbian, randomized, and Oja-inspired layers; introducing a modified loss function; and applying multi-scale feature fusion with fuzzy attention to refine encoder representations. The proposed model is evaluated on the Al-Cast Detection X-ray dataset, which contains small components from high-pressure die-casting machines, and the PCB quality inspection dataset, which features tiny hole anomalies. The results show that the optimized model achieves an mAP of 0.513 for small objects—an improvement from the 0.389 of the baseline RT-DETR model on the Al-Cast dataset—confirming its effectiveness. In addition, this paper contributes a mini-literature review of recent RT-DETR enhancements, situating our work within current research trends and providing context for future development.