MULTI-SCALE SAMPLE SELECTION BASED ON STATISTICAL CHARACTERISTICS FOR OBJECT DETECTION

In the domain of object detection, automatically selecting positive and negative samples methods have become a hot research topic in recent years. However, most of them focus on improving the sampling process but ignore the relationship between object size and feature map, in which the shallow and deep feature layers can capture small and large size objects well respectively. In this paper, we propose a multi-scale sample selection based on statistical characteristics for object detection. To improve the robustness of the Intersection over Union (IoU) threshold, we design a multi-scale sample selection module (MSSM), which takes full advantage of different feature layers. Besides, we introduce a multi-scale attention module (MSAM) by embedding in the feature pyramid networks (FPN) to improve the efficiency of feature fusion. Experiments on MS COCO dataset demonstrate that our method achieves significant improvement over the state-of-the-art methods.

Automated summary

In this paper, a multi-scale sample selection method based on statistical characteristics for object detection is proposed, with the design of a multi-scale sample selection module (MSSM) and a multi-scale attention module (MSAM) embedded in the feature pyramid networks (FPN). Experiments on MS COCO dataset show significant improvement over state-of-the-art methods.