Abstract
Small object detection is widely used in industries, military, autonomous driving and other fields. However, the accuracy of existing detection models in small object detection needs to be improved. This paper proposes the SC-AttentionIoU loss function to stress the issue. Due to the less features of small objects, SC-AttentionIoU introduces attention within the true bounding box, allowing the existing detection models to focus on the critical features of small objects. Besides, considering attention perhaps ignore non-critical features, SC-AttentionIoU proposes an adjustment factor to balance the critical and non-critical feature areas. Using the YOLOv5s model as a baseline, compared with the widely used CIoU, SC-AttentionIoU achieved an average improvement of 1% in mAP@.5 on the SSDD dataset and an average improvement of 1.47% in mAP@.5 on the PCB dataset in this experiment.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection (2020)
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers (2020)
Chu, X., et al.: Twins: revisiting the design of spatial attention in vision transformers (2021)
Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding YOLO series in 2021 (2021)
He, J., Erfani, S., Ma, X., Bailey, J., Chi, Y., Hua, X.S.: Alpha-IoU: a family of power intersection over union losses for bounding box regression (2022)
Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design (2021)
Li, J., et al.: Next-ViT: next generation vision transformer for efficient deployment in realistic industrial scenarios (2022)
Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows (2021)
Prathima, G., Lakshmi, A.Y.N., Kumar, C.V., Manikanta, A., Sandeep, B.J.: Defect detection in PCB using image processing. Int. J. Adv. Sci. Technol. 29(4) (2020)
Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression (2019)
Xu, S., et al.: PP-YOLOE: an evolved version of YOLO (2022)
Xu, X., Jiang, Y., Chen, W., Huang, Y., Zhang, Y., Sun, X.: DAMO-YOLO: a report on real-time object detection design (2023)
Yang, L., Zhong, J., Zhang, Y., Bai, S., Li, G., Yang, Y., Zhang, J.: An improving faster-RCNN with multi-attention ResNet for small target detection in intelligent autonomous transport with 6G. IEEE Trans. Intell. Transp. Syst., 1–9 (2022). https://doi.org/10.1109/TITS.2022.3193909
Yu, G., et al.: PP-PicoDet: a better real-time object detector on mobile devices (2021)
Yu, J., Jiang, Y., Wang, Z., Cao, Z., Huang, T.: UnitBox: an advanced object detection network. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 516–520 (2016). https://doi.org/10.1145/2964284.2967274
Zhang, T., et al.: SAR Ship Detection Dataset (SSDD): official release and comprehensive data analysis. Remote Sensing 13(18), 3690 (2021). https://doi.org/10.3390/rs13183690
Zhang, Y.F., Ren, W., Zhang, Z., Jia, Z., Wang, L., Tan, T.: Focal and efficient IOU loss for accurate bounding box regression (2022)
Zhao, W., Kang, Y., Chen, H., Zhao, Z., Zhai, Y., Yang, P.: A target detection algorithm for remote sensing images based on a combination of feature fusion and improved anchor. IEEE Trans. Instrum. Meas. 71, 1–8 (2022). https://doi.org/10.1109/TIM.2022.3181927
Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-IoU loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34(07), pp. 12993–13000 (2020). https://doi.org/10.1609/aaai.v34i07.6999
Acknowledgements
This work was supported by Key R &D Program of Shan dong Province, China (2022RZB02012), the Taishan Scholars Program (NO. tscy2 0221110).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhou, M., Yi, C., Li, M., Wan, H., Li, G., Han, D. (2023). Transforming Limitations into Advantages: Improving Small Object Detection Accuracy with SC-AttentionIoU Loss Function. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14260. Springer, Cham. https://doi.org/10.1007/978-3-031-44195-0_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-44195-0_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44194-3
Online ISBN: 978-3-031-44195-0
eBook Packages: Computer ScienceComputer Science (R0)