MFFAMM: A Small Object Detection with Multi-Scale Feature Fusion and Attention Mechanism Module

Abstract

Aiming at the low detection accuracy and poor positioning for small objects of single-stage object detection algorithms, we improve the backbone network of SSD (Single Shot MultiBox Detector) and present an improved SSD model based on multi-scale feature fusion and attention mechanism module in this paper. Firstly, we enhance the feature extraction ability of the shallow network through the feature fusion method that is beneficial to small object recognition. Secondly, the RFB (Receptive Field block) is used to expand the object’s receptive field and extract richer semantic information. After feature fusion, the attention mechanism module is added to enhance the feature information of important objects and suppress irrelevant other information. The experimental results show that our algorithm achieves 80.7% and 51.8% mAP on the PASCAL VOC 2007 classic dataset and MS COCO 2017 dataset, which are 3.2% and 10.6% higher than the original SSD algorithm. Our algorithm greatly improves the accuracy of object detection and meets the requirements of real-time.

Keywords

• small object detection
• multi-scale
• feature fusion
• attention mechanism
• receptive field