End to End Fusion Network of Deep and Hand Crafted Features for Small Object Detection

End to End Fusion Network of Deep and Hand Crafted Features for Small Object Detection

Abstract:

Recent advances in deep learning have enabled state-of-the-art performance in detecting medium and large-size objects. However, small object detection remains challenging primarily due to the scarcity of information. This paper proposes an end-to-end fusion network that integrates deep and hand-crafted features to address this limitation. A fusion module based on semantic context information is designed to enhance feature discrimination ability. Additionally, we introduce a kind of feature-contrast loss to incorporate prior knowledge into the learning of deep feature according to contrastive learning. Experiments on MS COCO (34.4% {\mathrm {A}}{{\mathrm {P}}_{\mathrm {S}}} ) and PASCAL VOC (85.9% mAP) datasets demonstrate that our approach achieves improved detection accuracy over previous methods, especially for small objects.