ITFD: an instance-level triplet few-shot detection network under weighted pair-resampling

Springer Science and Business Media LLC - Tập 53 - Trang 22728-22742 - 2023
Xin Chen1, Chaoyong Peng1, Chunrong Qiu1, Lin Luo1, Deqing Huang2, Ziyi Liu2
1School of Physical Science and Technology, Southwest Jiaotong University, Chengdu, China
2Institute of Systems Science and Technology, School of Electrical Engineering, Southwest Jiaotong University, Chengdu, China

Tóm tắt

Few-shot object detection has been widely applied in industrial applications, endangered detection, tumor lesion detection, etc. Although many excellent few-shot detection models have been proposed recently, intra-class & inter-class confusion and low activation of novel classes still keep few-shot detection challenging. In this paper, we propose a novel few-shot detection model ITFD, in which a weighted pair-resampling method improves the localization efficiency of the novel-class and a hard triplet loss reduces intra-class & inter-class confusion are contained. Extensive experiments have shown that our model achieves 3.6 $$\%$$ , 2.6 $$\%$$ , and 3.7 $$\%$$ average nAP50 improvement on novel-class setup 1,2,3 of PASCAL VOC compared to the same one-time fine-tuning type of models. Besides, to verify the effectiveness of our model in practical application, we established two train component detection datasets. Our model achieves state-of-the-art performance on both datasets with an average nAP50 improvement of 7 $$\%$$ and 4.8 $$\%$$ respectively.

Tài liệu tham khảo

Antonelli S, Avola D, Cinque L, Crisostomi D, Foresti GL, Galasso F, Marini MR, Mecca A, Pannone D (2022) Few-shot object detection: A survey. ACM Comput Surv 54(11s):1–37 Meng Y, Xu H, Ma Z, Zhou J, Hui D (2022) Detail-semantic guide network based on spatial attention for surface defect detection with fewer samples. Appl Intel Wang M, Ning H, Liu H Object detection based on few-shot learning via instance-level feature correlation and aggregation. Appl Intel 1–18 Zhang C, Bengio S, Hardt M, Recht B, Vinyals O (2021) Understanding deep learning (still) requires rethinking generalization. Commun ACM 64(3):107–115 Wang Y, Yao Q, Kwok JT, Ni LM (2020) Generalizing from a few examples: a survey on few-shot learning. ACM Comput Surv 53(3):1–34 Zhang G, Luo Z, Cui K, Lu S, Xing EP (2022) Meta-detr: image-level few-shot detection with inter-class correlation exploitation. IEEE Trans Pattern Anal Mach Intel Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. Adv Neural Info Process Syst 28 Fang W, Wang L, Ren P (2019) Tinier-yolo: a real-time object detection method for constrained environments. IEEE Access 8:1935–1944 Huang Z, Wang J, Fu X, Yu T, Guo Y, Wang R (2020) Dc-spp-yolo: dense connection and spatial pyramid pooling based yolo for object detection. Info Sci 522:241–258 Wen G, Cao P, Wang H, Chen H, Liu X, Xu J, Zaiane O (2022) Ms-ssd: multi-scale single shot detector for ship detection in remote sensing images. Appl Intel 1–19 Liu Y, Ma Z, Liu X, Ma S, Ren K (2019) Privacy-preserving object detection for medical images with faster r-cnn. IEEE Trans Info Forensics Secur Fang F, Li L, Zhu H, Lim J-H (2019) Combining faster r-cnn and model-driven clustering for elongated object detection. IEEE Trans Image Process 29:2052–2065 Gong H, Mu T, Li Q, Dai H, Li C, He Z, Wang W, Han F, Tuniyazi A, Li H et al (2022) Swin-transformer-enabled yolov5 with attention mechanism for small object detection on satellite images. Remote Sens 14(12):28–61 Dai Z, Cai B, Lin Y, Chen J (2022) Unsupervised pre-training for detection transformers. IEEE Trans Pattern Anal Mach Intell Duan R, Li D, Tong Q, Yang T, Liu X, Liu X (2021) A survey of few-shot learning: an effective method for intrusion detection. Secur Commun Netw 2021 López-Martín M, Carro B, Sánchez-Esguevillas A (2019) Variational data generative model for intrusion detection. Knowl Inf Syst Ye H-J, Sheng X-R, Zhan D-C (2020) Few-shot learning with adaptively initialized task optimizer: a practical meta-learning approach. Mach Learn 109(3):643–664 Li X, Sun Z, Xue J-H, Ma Z (2021) A concise review of recent few-shot meta-learning methods. Neurocomputing 456:463–468 Thung K-H, Wee C-Y (2018) A brief review on multi-task learning. Multimed Tools Appl 77(22):29705–29725 Altae-Tran H, Ramsundar B, Pappu AS, Pande V (2017) Low data drug discovery with one-shot learning. ACS Central Sci 3(4):283–293 Chen H, Wang Y, Wang G, Qiao Y (2018) Lstd: a low-shot transfer detector for object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 32 Xiao Y, Marlet R (2020) Few-shot object detection and viewpoint estimation for objects in the wild. In: European Conference on Computer Vision, pp 192–210 . Springer Sun B, Li B, Cai S, Yuan Y, Zhang C (2021) Fsce: Few-shot object detection via contrastive proposal encoding. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 7352–7362 Wang X, Huang T, Gonzalez J, Darrell T, Yu F (2020) Frustratingly simple few-shot object detection. In: International Conference on Machine Learning, pp 9919–9928. PMLR Yang Z, Wang Y, Chen X, Liu J, Qiao Y (2020) Context-transformer: tackling object confusion for few-shot detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 34, pp 12653–12660 Yan X, Chen Z, Xu A, Wang X, Liang X, Lin L (2019) 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 Fan Q, Zhuo W, Tang C-K, Tai Y-W (2020) Few-shot object detection with attention-rpn and multi-relation detector. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 4013–4022 Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vision 88(2):303–338 Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P, Zitnick CL (2014) Microsoft coco: common objects in context. In: European Conference on Computer Vision, pp 740–755. Springer Wang Y-X, Ramanan D, Hebert M (2019) Meta-learning to detect rare objects. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 9925–9934 Zhang W, Wang Y-X (2021) Hallucination improves few-shot object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 13008–13017 Xia R, Li G, Huang Z, Meng H, Pang Y (2023) Bi-path combination yolo for real-time few-shot object detection. Pattern Recogn Lett 165:91–97 Vu A-KN, Nguyen N-D, Nguyen K-D, Nguyen V-T, Ngo TD, Do T-T, Nguyen TV (2022) Few-shot object detection via baby learning. Image Vision Comput 120:104–398 Kang B, Liu Z, Wang X, Yu F, Feng J, Darrell T (2019) Few-shot object detection via feature reweighting. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 8420–8429 Chen T-I, Liu Y-C, Su H-T, Chang Y-C, Lin Y-H, Yeh J-F, Chen W-C, Hsu W (2021) Dual-awareness attention for few-shot object detection. IEEE Trans Multimedia Hayashi T, Fujita H, Hernandez-Matamoros A (2021) Less complexity one-class classification approach using construction error of convolutional image transformation network. Inf Sci 560:217–234 Hayashi T, Cimr D, Studnička F, Fujita H, Bušovskỳ D, Cimler R (2022) Ocstn: one-class time-series classification approach using a signal transformation network into a goal signal. Inf Sci 614:71–86 Ouyang Y, Wang X-Q, Hu R-Z, Xu H-H (2022) Few-shot object detection based on positive-sample improvement. Def Technol