journal article·2025-03-28Open access

Study on Few-Shot Object Detection Approach Based on Improved RPN and Feature Aggregation

Qiyu Pan, Keyi Fu, Gaocai Wang

Applied Sciences· Volume 15· Issue 7

Abstract

In this paper, we propose an improved Region Proposal Network (RPN) by introducing a metric-based nonlinear classifier to compute the similarity between features extracted from the backbone network and those of new classes. This enhancement aims to improve the detection precision for candidate boxes of new classes and filter out candidate boxes with high Intersection of Union (IoU). Simultaneously, we introduce an attention-based Feature Aggregation Module (AFM) in Region of Interest (RoI) Align to aggregate feature information from different levels, obtaining more comprehensive information and feature representation to address the issue of missing feature information due to scale differences. Combining these two improvements, we present a novel few-shot object detection algorithm—IFA-FSOD. We conduct extensive experiments on datasets. Compared to some mainstream few-shot object detection algorithms, the IFA-FSOD algorithm can select more accurate candidate boxes, addressing issues of missed high IoU candidate boxes and incomplete feature information capture, resulting in higher precision.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Advanced Neural Network Applications · Industrial Vision Systems and Defect Detection · Domain Adaptation and Few-Shot Learning

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

School of Artificial Intelligence, Sun Yat-sen University, Guangzhou 510275, China

School of Computer and Electronics Information, Guangxi University, Nanning 530004, China

Funding

National Natural Science Foundation of China

References (33)

Show source-provided references
1. A review of research on small sample object detection
2. Few-shot object detection: Research advances and challenges10.1016/j.inffus.2024.102307 ↗
3. Huang, Y., Dou, H., and Xiao, G. (2024, June 15). Small Sample Object Detection Combining Classification Correction and Sample Amplification. Computer Engineering and Applications: 1-10 2023 [2022-11-20]. Available online: http://kns.cnki.net/kcms/detail/11.2127.TP.20221104.1529.020.html.
4. Kohler, M., Eisenbach, M., and Gross, H.-M. (2024, June 15). Few-Shot Object Detection: A Comprehensive Survey. [EB/OL]. [2023-11-10]. Available online: https://arxiv.org/pdf/2112.11699v2.pdf.
5. Kang, B., Liu, Z., Wang, X., Yu, F., Feng, J., and Darrell, T. (November, January 27). Few-shot object detection via feature reweighting. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.10.1109/ICCV.2019.00851 ↗
6. Wang, X., Huang, T.E., Darrell, T., Gonzalez, J.E., and Yu, F. (2020, January 13–18). Frustratingly simple few-shot object detection. Proceedings of the 2020 International Conference on Machine Learning, Virtual.
7. Yan, X., Chen, Z., Xu, A., Wang, X., Liang, X., and Lin, L. (November, January 27). Meta r-cnn: Towards general solver for instance-level low-shot learning. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.10.1109/ICCV.2019.00967 ↗
8. Faster R-CNN: Towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
9. Hu, H., Bai, S., Li, A., Cui, J., and Wang, L. (2021, January 20–25). Dense relation distillation with context—Aware aggregation for few-shot object detection. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01005 ↗
10. Meta faster r-cnn: Towards accurate few-shot object detection with attentive feature alignment10.1609/aaai.v36i1.19959 ↗
11. Jeune, P.L., and Mokraoui, A. (2024, June 15). A Comparative Attention Framework for Better Few-Shot Object Detection on Aerial Images. [EB/OL]. [2023-11-10]. Available online: https://arxiv.org/pdf/2210.13923.pdf.
12. Feature reconstruction and metric based network for few-shot object detection10.1016/j.cviu.2022.103600 ↗
13. Li, A., and Li, Z. (2021, January 20–25). Transformation Invariant Few-Shot Object Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.00311 ↗
14. Li, B., Yang, B., Liu, C., Liu, F., Ji, R., and Ye, Q. (2021, January 20–25). Beyond Max-Margin: Class Margin Equilibrium for Few-Shot Object Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.00728 ↗
15. Han, G., Ma, J., Huang, S., Chen, L., and Chang, S.F. (2022, January 18–24). Few-shot object detection with fully cross-transformer. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.00525 ↗
16. Few-shot object detection and viewpoint estimation for objects in the wild
17. Fan, Q., Zhuo, W., Tang, C.K., and Tai, Y.W. (2020, January 13–19). Few-shot object detection with Attention-RPN and multi-relation detector. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00407 ↗
18. Zhang, L., Zhou, S., Guan, J., and Zhang, J. (2021, January 20–25). Accurate few-shot object detection with support-query mutual guidance and hybrid loss. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.01419 ↗
19. Han, G., He, Y., Huang, S., Ma, J., and Chang, S.F. (2021, January 20–25). Query adaptive few-shot object detection with heterogeneous graph convolutional networks. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, Nashville, TN, USA.10.1109/ICCV48922.2021.00325 ↗
20. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature pyramid networks for object detection. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
21. Fan, Z., Ma, Y., Li, Z., and Sun, J. (2021, January 20–25). Generalized few-shot object detection without forgetting. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.00450 ↗
22. Han, J., Ren, Y., Ding, J., Yan, K., and Xia, G.S. (203, January 7–14). Few-Shot Object Detection via Variational Feature Aggregation. Proceedings of the 2023 AAAI Conference on Artificial Intelligence, Washington, DC, USA.
23. Sun, B., Li, B., Cai, S., Yuan, Y., and Zhang, C. (2021, January 20–25). Fsce: Few-shot object detection via contrastive proposal encoding. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.00727 ↗
24. Zhu, C., Chen, F., Ahmed, U., Shen, Z., and Savvides, M. (2021, January 20–25). Semantic relation reasoning for shot-stable few-shot object detection. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.00867 ↗
25. Qiao, L., Zhao, Y., Li, Z., Qiu, X., Wu, J., and Zhang, C. (2021, January 20–25). DeFRCN: Decoupled Faster R-CNN for few-shot object detection. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, Nashville, TN, USA.10.1109/ICCV48922.2021.00856 ↗
26. Kaul, P., Xie, W., and Zisserman, A. (2022, January 18–24). Label, verify, correct: A simple few shot object detection method. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.01384 ↗
27. He, K., Zhang, X., Ren, S., and Sun, J. (2022, January 18–24). Deep residual learning for image recognition. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.
28. The Pascal Visual Object Classes (VOC) challenge10.1007/s11263-009-0275-4 ↗
29. The Pascal visual object classes challenge: A retrospective10.1007/s11263-014-0733-5 ↗
30. Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C.L. (2014). Microsoft coco: Common objects in context. Proceedings of the Computer Vision ECCV 2014: 13th European Conference, Zurich, Switzerland, 6–12 September 2014, Proceedings, Part V 13, Springer.
31. Wang, Y.X., Ramanan, D., and Hebert, M. (November, January 27). Meta-learning to detect rare objects. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.10.1109/ICCV.2019.01002 ↗
32. DA-FSOD:A Novel Augmentation Scheme for Few-Shot Object Detection10.1109/ACCESS.2023.3307490 ↗
33. Wu, J., Liu, S., Huang, D., and Wang, Y. (2020). Multi-scale positive sample refinement for few-shot object detection. Proceedings of the 2020 European Conference on Computer Vision—ECCV 2020: 16th European Conference, Glasgow, UK, 23–28 August 2020, Proceedings, Part XVI 16, Springer.