Non-Maximum Suppression Guided Label Assignment for Object Detection in Crowd Scenes

The detection performance in crowd scenes is limited by recalling hard objects (e.g., occluded objects). It requires that this kind of objects can be successfully detected and retained by the non-maximum suppression (NMS) while controlling false positives. The existing dynamic label assignment algorithms can help recall these objects by adaptively allocating appropriate positive samples, however, they ignore the alignment with the selecting rules of NMS. This leads to the fact that detecting objects in crowd scenes are still very sensitive to the NMS threshold setting. As a result, the existing methods can only set a low NMS threshold to avoid the excessive false positives, causing some objects failed to be recalled. And these methods also generally lack more excitation for positive samples, which hinders further facilitating the recall of hard instances in crowd scenes. This article proposes a novel dynamic label assignment strategy for object detection in crowd scenes, called non-maximum suppression guided label assignment (NGLA), which aligns the assignment strategy with NMS process and learns more prominent positive samples. Following NMS, NGLA introduces the IoU between samples with their corresponding best samples to define positive and negative samples. To cooperate with NGLA, an NMS-aware loss is proposed to dynamically assign sample weights when supervising sample predictions, which also considers the IoU with the best sample. In addition, for better classification prediction, a regression assisted classification branch is designed to help detectors perceive the relation between the regression predictions of each sample and the corresponding best sample. Experiments demonstrate that NGLA outperforms other label assignment methods on CrowdHuman and Citypersons, and is less sensitive to the NMS threshold in crowd scenes.