RFEM: Remote Feature Enhancement Module for Target Detection

Abstract

The research and development of dense crowd detection technology have always been one of the hot and challenging topics in the field of computer vision. DETR-like models have shown good performance in both training efficiency and inference capabilities. Nevertheless, as the optimization proceeds, these models can demonstrate sparse long-range feature correlations. This paper presents a specialized long-range feature enhancement module intended for optimizing DETR-like detection models. By utilizing an optimized PVM clustering algorithm, the robustness of the model is enhanced, and linear attention is incorporated into the aggregated tokens to reinforce long-range feature relationships. Besides, our method maintains the connections between occluded segmentation features during both training and inference phases. It also enhances the detection accuracy of small targets without increasing computational overhead. We conducted experiments on the COCO 2017 and the CrowdHuman datasets, and extensive experimental results demonstrate the effectiveness of our proposed method.