Class-Wise FM-NMS for Knowledge Distillation of Object Detection

Abstract

The trade-off between accuracy and speed for an object detection model is important. When we implement an object detection model in embedded devices, a lightweight model can accelerate the detection speed. Meanwhile, the detection accuracy will be decreased. In this paper, we propose a knowledge distillation method for a lightweight object detection model. The proposed method introduces an improved feature map novel non-maximum suppression (FM-NMS) method. The improved FM-NMS uses different focus size with respect to each object class, which can suppress false positives and improve detection accuracy. In our experiments, we use onestage object detection methods, YOLOv4 as a teacher model and YOLOv4-tiny as a student model, and we apply the proposed method to them. The experimental results demonstrate that the proposed method improves the detection accuracy of the student model while maintaining the lightweight model size.