HIC-YOLOv5: Improved YOLOv5 For Small Object Detection

TL;DR

HIC-YOLOv5 is an enhanced small object detection model that improves accuracy while maintaining low computational cost by adding a prediction head, involution block, and CBAM attention mechanism.

Contribution

The paper introduces HIC-YOLOv5, a novel small object detection model that balances high accuracy with low computational cost through specific architectural modifications.

Findings

Improved mAP@[.5:.95] by 6.42% on VisDrone-2019-DET dataset

Enhanced mAP@0.5 by 9.38% with the proposed modifications

Achieved better detection performance with lower computation cost

Abstract

Small object detection has been a challenging problem in the field of object detection. There has been some works that proposes improvements for this task, such as adding several attention blocks or changing the whole structure of feature fusion networks. However, the computation cost of these models is large, which makes deploying a real-time object detection system unfeasible, while leaving room for improvement. To this end, an improved YOLOv5 model: HIC-YOLOv5 is proposed to address the aforementioned problems. Firstly, an additional prediction head specific to small objects is added to provide a higher-resolution feature map for better prediction. Secondly, an involution block is adopted between the backbone and neck to increase channel information of the feature map. Moreover, an attention mechanism named CBAM is applied at the end of the backbone, thus not only decreasing the computation cost compared with previous works but also emphasizing the important information in both channel and spatial domain. Our result shows that HIC-YOLOv5 has improved mAP@[.5:.95] by 6.42% and mAP@0.5 by 9.38% on VisDrone-2019-DET dataset.