HIC-YOLOv5: Improved YOLOv5 For Small Object Detection
This work addresses the problem of real-time small object detection for applications like drone-based systems, though it is incremental as it builds on YOLOv5 with specific modifications.
The paper tackled small object detection by proposing HIC-YOLOv5, an improved YOLOv5 model that adds a small object prediction head, uses an involution block, and applies CBAM attention, resulting in a 6.42% increase in mAP@[.5:.95] and 9.38% in mAP@0.5 on the VisDrone-2019-DET dataset.
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.