Abstract
The anchor-free object detection method avoids the complex hyper-parameter setting problem of the traditional anchor-based method, and has more advantages in accuracy and speed. However, it still has some problems such as low precision of small-scale object detection and poor detection result under complex background. To solve this problem, an improved anchor-free object detection method based on FCOS is proposed in this paper. By adding an efficient channel attention mechanism module to the feature extraction network and using a local cross-channel interaction strategy without dimensionality reduction, the 1D convolution kernel size is adaptively selected to obtain useful dependencies between channels and improve feature extraction capability. A context extraction module is designed in feature fusion network to explore context information from multiple receptive fields and improve classification accuracy. In the training stage, DIoU loss is used to make the regression of the border more stable and accurate, and the training process converges faster. The proposed method is evaluated on COCO2017. The experimental results show that compared with the baseline FCOS method, the average accuracy of the proposed method is improved by 1.3%, which has advantages in comprehensive performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Cai, Z., Vasconcelos, N.: Cascade r-cnn: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154–6162 (2018)
Cao, J., Chen, Q., Guo, J., Shi, R.: Attention-guided context feature pyramid network for object detection. arXiv preprint arXiv:2005.11475 (2020)
Dai, J., Li, Y., He, K., Sun, J.: R-fcn: object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016)
De Boer, P.T., Kroese, D.P., Mannor, S., Rubinstein, R.Y.: A tutorial on the crossentropy method. Ann. Oper. Res. 134, 19–67 (2005)
Dong, Z., Li, G., Liao, Y., Wang, F., Ren, P., Qian, C.: Centripetalnet: pursuing high-quality keypoint pairs for object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10519–10528 (2020)
Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: Centernet: keypoint triplets for object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6569–6578 (2019)
Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Huang, L., Yang, Y., Deng, Y., Yu, Y.: Densebox: unifying landmark localization with end to end object detection. arXiv preprint arXiv:1509.04874 (2015)
Kong, T., Sun, F., Liu, H., Jiang, Y., Li, L., Shi, J.: Foveabox: beyound anchor-based object detection. IEEE Trans. Image Process. 29, 7389–7398 (2020)
Law, H., Deng, J.: Cornernet: detecting objects as paired keypoints. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 734–750 (2018)
Lin, T.Y., Doll´ar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll´ar, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)
Lin, TY., et al.: Microsoft coco: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision – ECCV 2014. ECCV 2014, LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., Lin, D.: Libra r-cnn: towards balanced learning for object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 821–830 (2019)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)
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. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 658–666 (2019)
Sun, P., et al.: Sparse r-cnn: end-to-end object detection with learnable proposals. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14454–14463 (2021)
Tian, Z., Shen, C., Chen, H., He, T.: Fcos: fully convolutional one-stage object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9627–9636 (2019)
Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: Eca-net: efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11534–11542 (2020)
Yan, X., Chen, Z., Xu, A., Wang, X., Liang, X., Lin, L.: Meta r-cnn: towards general solver for instance-level low-shot learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9577–9586 (2019)
Zand, M., Etemad, A., Greenspan, M.: ObjectBox: from centers to boxes for anchor-free object detection. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision – ECCV 2022. ECCV 2022. LNCS, vol. 13670, pp. 390–406. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-20080-9_23
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, pp. 12993–13000 (2020)
Zheng, Z., et al.: Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Trans. Cybern. 52(8), 8574–8586 (2021)
Zhou, X., Koltun, V., Krähenbühl, P.: Probabilistic two-stage detection. arXiv preprint arXiv:2103.07461 (2021)
Zhu, C., He, Y., Savvides, M.: Feature selective anchor-free module for single-shot object detection. In: Proceedings of the IEEE/CVF Conference on Computer vision and Pattern Recognition, pp. 840–849 (2019)
Acknowledgements
This work was partially supported by the National Natural Science Foundation of China (Grant Nos. 62362014, 62172120, and 62002082), and the Guangxi Natural Science Foundation of China (Grant Nos. 2019GXNSFAA245014, 2020GXNSFBA238014).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, H., Yang, R., Lan, R., Luo, X. (2024). AF-FCOS: An Improved Anchor-Free Object Detection Method. In: Huang, DS., Premaratne, P., Yuan, C. (eds) Applied Intelligence. ICAI 2023. Communications in Computer and Information Science, vol 2014. Springer, Singapore. https://doi.org/10.1007/978-981-97-0903-8_26
Download citation
DOI: https://doi.org/10.1007/978-981-97-0903-8_26
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-0902-1
Online ISBN: 978-981-97-0903-8
eBook Packages: Computer ScienceComputer Science (R0)