Few-shot Object Detection via Refining Eigenspace
Authors: 
Yan Ouyang, Xinqing Wang, Honghui Xu, Ruizhe Hu, Faming Shao, Dong WangAuthors Info & Claims
Yan Ouyang, Xinqing Wang, Honghui Xu, Ruizhe Hu, Faming Shao, Dong WangAuthors Info & ClaimsPages 86 - 94
Abstract
Few-shot object detection (FSOD) aims to retain the performance of detector when only given scarce annotated instances. We reckon that its difficulty lies in the fact that the scare positive samples restrict the accurate construction of the eigenspace of involved categories. In this paper, we proposed a novel FSOD detector based on refining the eigenspace, which is implemented through a pure positive augmentation, a full feature mining module and a modified loss function. The pure positive augmentation expands the quantity and enriches the scale distribution of positive samples, inhibiting the expansion of negative samples. The full feature mining module enables the model to mining more information about objects. The modified loss function drives prediction results closer to ground truths. We apply these two improvements to YOLOv4, the representative of one-stage detector, which is termed YOLOv4-FS. On PASCAL VOC and MS COCO datasets, our YOLOv4-FS achieves competitive performance compared with existing progressive detectors.
References
[1]
S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6):1137-1149.
[2]
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, You Only Look Once: Unified, Real-Time Object Detection[C] Computer Vision & Pattern Recognition. IEEE, 2016. pp. 779-788.
[3]
W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu and A. C. Berg, 2016. Ssd: Single shot multibox detector. In ECCV, 21–37. Springer.
[4]
Kim, G., H. G. Jung, and S. W. Lee . "Spatial Reasoning for Few-Shot Object Detection." Pattern Recognition 11(2021):108118.
[5]
B. Kang, Z. Liu, X. Wang, F. Yu, J. Feng, and T. Darrell, “Few-Shot Object Detection via Feature Reweighting," 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 2019, pp. 8419-8428.
[6]
Liu. S, Qi. L, Qin. HF, Shi. JQ and Jia. JY. Path aggregation network for instance segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 8759–8768, 2018.
[7]
He. K, Zhang. XY, Ren. XQ and Sun J. Spatial pyramid pooling in deep convolutional networks for visual recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 37(9):1904–1916, 2015.
[8]
Z. Liu, G. Gao, L. Sun, and L. Fang, "IPG-Net: Image Pyramid Guidance Network for Small Object Detection," 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA, 2020, pp. 4422-4430.
[9]
Y. Pang, T. Wang, R. M. Anwer, F. S. Khan, and L. Shao "Efficient Featurized Image Pyramid Network for Single Shot Detector," 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019, pp. 7328-7336.
[10]
X. Shen, Y.C. Chen, X. Tao, and J. Jia, “Convolutional Neural Pyramid for Image Processing. 2017,” arXiv preprint arXiv:1704.02071v1 [cs.CV] 7 Apr 2017.
[11]
Yun. S, Han. D, Oh. SJ, Chun. S, Choe. J and Yoo. Y. CutMix: Regularization strategy to train strong classifiers with localizable features, In Proceedings of the IEEE International Conference on Computer Vision (ICCV), pages 6023–6032, 2019.
[12]
A. Bochkovskiy, C.Y. Wang and H.Y.M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection[J].,” 2020. arXiv preprint arXiv:2004.10934v1 [cs.CV] 23 Apr 2020.
[13]
Y. X. Wang, D. Ramanan and M. Hebert, "Meta-Learning to Detect Rare Objects," 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 9924-9933.
[14]
S. Gidaris, and N. Komodakis, “Dynamic few-shot visual learning without forgetting,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4367–4375, 2018.
[15]
J. Redmon and A. Farhadi "YOLO9000: Better, Faster, Stronger," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017, pp. 6517-6525.
[16]
X. Wang, T.E. Huang, T. Darrell, J.E. Gonzalez, and F. Yu, “Frustratingly Simple Few-Shot Object Detection[J],” 2020. arxiv preprint arXiv:2003.06957v1 [cs.CV] 16 Mar 2020.
[17]
H. Chen, Y. Wang, G. Wang and Y. Qiao, “LSTD: A low-shot transfer detector for object detection,” 2018. arXiv preprint arXiv:1803.01529v1 [cs.CV] 5 Mar 2018.
[18]
Q. Fan, W. Zhuo, C. K. Tang, and Y. W. Tai, "Few-Shot Object Detection With Attention-RPN and Multi-Relation Detector," 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2020, pp. 4012-4021.
[19]
X. Yan, Z. Chen, A. Xu, X. Wang, X. Liang, and L. Lin, “Meta R-CNN: Towards general solver for instance-level low-shot learning,” 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 2019, pp. 9576-9585.
[20]
G. Kim, H. -G. Jung and S. -W. Lee, "Few-Shot Object Detection via Knowledge Transfer," 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Toronto, ON, 2020, pp. 3564-3569.
[21]
Z. Fan, Y. Ma, Z. Li, and J. Sun, “Generalized Few-Shot Object Detection without Forgetting,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[22]
B. Singh and L. S. Davis. An analysis of scale invariance in object detection - SNIP. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018.
[23]
B. Singh, M. Najibi, L.S. Davis, SNIPER: efficient multi-scale training. In: Advances in Neural Information Processing Systems (NIPS) (2018).
Index Terms
- Few-shot Object Detection via Refining Eigenspace
Recommendations
Robust Few-Shot Graph Anomaly Detection via Graph Coarsening
Knowledge Science, Engineering and ManagementAbstractGraph anomaly detection is an important aspect of anomaly detection, especially the graph-level anomaly detection, which can be used into biomolecular research or drug molecular detection and so on. It is necessary to identify anomalies within a ...
Open-World Few-Shot Object Detection
Advanced Intelligent Computing Technology and ApplicationsAbstractGeneral object detection has made significant progress under the close-set setting. However, the detector can only support a fixed set of categories and fail to identify unknown objects in real-world scenarios. Therefore, class-agnostic object ...
Restoring negative information in few-shot object detection
NIPS '20: Proceedings of the 34th International Conference on Neural Information Processing SystemsFew-shot learning has recently emerged as a new challenge in the deep learning field: unlike conventional methods that train the deep neural networks (DNNs) with a large number of labeled data, it asks for the generalization of DNNs on new classes with ...
Comments
Information & Contributors
Information
Published In
November 2022
683 pages
ISBN:9781450397056
DOI:10.1145/3581807
Copyright © 2022 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 22 May 2023
Check for updates
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ICCPR 2022
ICCPR 2022: 2022 11th International Conference on Computing and Pattern Recognition
November 17 - 19, 2022
Beijing, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 16Total Downloads
- Downloads (Last 12 months)13
- Downloads (Last 6 weeks)2
Reflects downloads up to 30 Aug 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format