Multilevel receptive field expansion network for small object detection

Small object detection remains a bottleneck because there is little visual information about them, especially in the deep layers. To improve the detection performance of small objects, here, Swin Transformer is introduced as the model backbone network to extract rich features of small objects. Then, a multilevel receptive field expansion network (MRFENet) is proposed based on the characteristics of different stages in the Swin Transformer. Specifically, a receptive field expansion block (RFEB) is designed to acquire contextual cues and extract detailed information. The RFEB is carefully designed to target the required receptive fields of different layers and further refine the features. MRFENet combined with RFEBs implements the retention of small object context cues and the acquisition of receptive fields for the adaptive detection tasks. Finally, a union loss function is designed to enhance the localization ability. Experiments on the MS COCO dataset demonstrate that the proposed MRFENet has a significant improvement against other state-of-the-art methods, which further validates that MRFENet can effectively utilize small object information.

Automated summary

This paper introduces a method to improve the detection performance of small objects by using Swin Transformer as the backbone network and proposing a multilevel receptive field expansion network (MRFENet). The MRFENet, combined with receptive field expansion blocks (RFEBs), retains small object context cues and acquires receptive fields for adaptive detection tasks. A union loss function is designed to enhance the localization ability. Experimental results on the MS COCO dataset show that MRFENet has a significant improvement compared to other state-of-the-art methods, validating its effectiveness in utilizing small object information.