In order to solve the problems of limited information that can be learned by the model due to the scarcity of training samples in few-shot scenarios, the performance of the model is restricted by the scale change of the object, and the catastrophic forgetting of the base class knowledge, a few-shot object detection algorithm with improved Faster R-CNN was proposed by following the transfer learning method. Firstly, in the feature extraction stage, the central coordinate attention mechanism was added to guide the model to learn the core features of the object, and multi-scale fusion and deformable convolution were introduced to enable the model to extract rich feature information on the feature map at different scales. Then, a gradual RPN was introduced, and a two-stage regression method was used to gradually optimize the generated regional suggestions. Finally, the knowledge compensation module was introduced to decouple the prior knowledge from the new knowledge with the help of the decoupling mechanism, so as to maintain a good memory of the base class. Experimental results show that, in the three novel class splits of the PASCAL VOC, compared with the mainstream small sample object detection method FSODCR, the proposed algorithm achieves an average increased in nAP by 8.37 percentage points and 6.63 percentage points in the 2-Shot and 5-Shot settings respectively; on the MS COCO, compared with FSODCR, the proposed algorithm achieves an average increase in nAP and nAP75 of 1.2 percentage points and 0.9 percentage points respectively under the 10-Shot, and nAP and nAP75 have increased by 1.2 percentage points and 0.8 percentage points under the 30-Shot, which significantly improves the accuracy and stability of object detection under few-shot conditions.
CHANGXinghua, WANGJianrong. Expression recognition algorithm based on optimized YOLOv7-tiny[J]. Journal of Test and Measurement Technology, 2025, 39(2): 113-120. (in Chinese)
[6]
FANW, DINGJ, PENGB, et al. Multi-scale fire target detection algorithm using YOLO-fire[J]. Journal of Measurement Science and Instrumentation, 2025, 16(4): 625-636.
SHIWei, WUJian. A multi-attribute evaluation method for low-altitude security system solutions based on DEMATEL and TOPSIS[J]. Science Technology and Engineering, 2025, 25(14): 6109-6117. (in Chinese)
CHENYina. Research on target tracking method based on computer vision technology[J]. Process Automation Instrumentation, 2025, 46(6): 48-52. (in Chinese)
LIHongbo, HEQixue, BAOShengli. Lightweight invasive species detection algorithm based on improved YOLOv8n[J]. Journal of Computer Applications, 2025, 45(S2): 278-286. (in Chinese)
[15]
KATZMANNA, TAUBMANNO, AHMADS, et al. Explaining clinical decision support systems in medical imaging using cycle-consistent activation maximization[J]. Neurocomputing, 2021, 458: 141-156.
CHAIRui, LUOYubing, QINPinle, et al. Colon cancer gland segmentation network based on edge fusion and multi scale feature enhancement[J]. Journal of North University of China (Natural Science Edition), 2025, 46(4): 411-421. (in Chinese)
SUNB, LIB, CAIS, et al. FSCE: Few-shot object detection via contrastive proposal encoding[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021: 7348-7358.
[20]
QIAOL, ZHAOY, LIZ, et al. DeFRCN: Decoupled faster R-CNN for few-shot object detection[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2022: 8661-8670.
[21]
KRISTANM, LUKEŽIČA, PELHANJ, et al. A novel unified architecture for low-shot counting by detection and segmentation[C]//Advances in Neural Information Processing Systems 37, 2024: 66260-66282.
[22]
ZHAOP, CHENJ, WANH, et al. Few-shot object detection for SAR images via context-aware and robust Gaussian flow representation[J]. Remote Sensing, 2025, 17(3): 391.
[23]
ZHANGG, LUOZ, CUIK, et al. Meta-DETR: Few-shot object detection via unified image-level meta-learning[DB/OL]. (2021-09-20) [2025-05-11].
[24]
KANGB, LIUZ, WANGX, et al. Few-shot object detection via feature reweighting[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019: 8419-8428.
[25]
YANX, CHENZ, XUA, et al. Meta R-CNN: Towards general solver for instance-level low-shot learning[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2020: 9576-9585.
[26]
XIAOY, LEPETITV, MARLETR. Few-shot object detection and viewpoint estimation for objects in the wild[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(3): 3090-3106.
[27]
WANGY X, RAMANAND, HEBERTM. Meta-learning to detect rare objects[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2020: 9924-9933.
[28]
CHENH, WANGY, WANGG, et al. LSTD: A low-shot transfer detector for object detection[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2018, 32(1): 2836-2843.