Incremental Object Detection based on YOLO v5 and EWC Models
Pages 452 - 457
Abstract
Current object detection models become increasingly sophisticated under the challenges of open domain. It is strongly needed to continuously learn new unseen images to achieving incremental object detection capacity. The existing methods mainly rely on two-stage object detection models which have shortcomings of time consuming and not real-time detection. In this paper, we propose a new incremental object detection model combining the real-time object detection model named YOLO with the incremental learning model EWC (Elastic Weight Consolidation), which is a posterior information-based model balancing the importance of new and old parameters. Our model modifies the loss function of YOLO and adds the EWC model as a regularization term. Experimental results validate the validity of our model on the Pascal VOC2012 datasets.
References
[1]
Girshick R, Donahue J, Darrell T, 2014.Rich feature hierarchies for accurate object detection and semantic segmentation[J]. Proceedings of the IEEE conference on computer vision and pattern recognition.
[2]
He K, Zhang X, Ren S, 2015. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(9): 1904-1916.
[3]
Girshick R. 2015. Fast r-cnn. Proceedings of the IEEE international conference on computer vision.
[4]
Ren S, He K, Girshick R, 2015. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. Advances in neural information processing systems, 28: 91-99.
[5]
Lin T Y, Dollar P, Girshick R, 2017. Feature pyramid networks for object detection[C]. Proceedings of the IEEE conference on computer vision and pattern recognition.
[6]
He K, Gkioxari G, Dollár P, 2017. Mask R-CNN. Proceedings of the IEEE international conference on computer vision.
[7]
Redmon J, Divvala S, Girshick R, 2016. You only look once: Unified, real-time object detection. Proceedings of the IEEE conference on computer vision and pattern recognition.
[8]
Bochkovskiy A, Wang C Y, Liao H Y M. 2020. YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934.
[9]
Chiasi G, Tsung-Yi Lin, Le Q V, Learning Scalable Feature Pyramid Architecture for Object Detection. Proceedings of the IEEE Computer Vision and Pattern Recognition.
[10]
Shah S A R, Tahir A, Yousaf M H, 2018. AmoebaNet: An SDN-enabled network service for big data science. Journal of Network and Computer Applications, 119: 70-82.
[11]
Kirkpatrick J, Pascanu R, Rabinowitz N, 2017. Overcoming catastrophic forgetting in neural networks. Proceedings of the national academy of sciences, 114(13): 3521-3526.
[12]
Zenke F, Poole B, Ganguli S. 2017. Continual learning through synaptic intelligence. International Conference on Machine Learning. PMLR, 3987-3995.
[13]
Zeng G, Chen Y, Cui B, 2019. Continual learning of context-dependent processing in neural networks. Nature Machine Intelligence, 1(8): 364-372.
[14]
He X, Jaeger H. 2018. Overcoming catastrophic interference using conceptor-aided backpropagation. International Conference on Learning Representations.
[15]
Li Z, Hoiem D. Learning without forgetting. IEEE transactions on pattern analysis and machine intelligence,
[16]
Peng C, Wang X, Gao C, 2021. SID: Incremental learning for anchor-free object detection via Selective and Inter-related Distillation. Computer Vision and Image Understanding, 210: 103229.
[17]
Li P, Chen J, Huang Q, 2021. Class-incremental few-shot object detection. arXiv preprint arXiv:2105.07637.
[18]
Liu Y, Schiele B, Vedaldi A and Rupprecht C. 2023. Continual Detection Transformer for Incremental Object Detection, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, 23799-23808.
[19]
Li Z, Xu P, Chang X, 2023. When Object Detection Meets Knowledge Distillation: A Survey, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 8: 10555-10579.
Index Terms
- Incremental Object Detection based on YOLO v5 and EWC Models
Recommendations
Object detection using YOLO: challenges, architectural successors, datasets and applications
AbstractObject detection is one of the predominant and challenging problems in computer vision. Over the decade, with the expeditious evolution of deep learning, researchers have extensively experimented and contributed in the performance enhancement of ...
A real-time object detection algorithm for video
AbstractDeep learning technology has been widely used in object detection. Although the deep learning technology greatly improves the accuracy of object detection, we also have the challenge of a high computational time. You Only Look Once (...
YOLO with adaptive frame control for real-time object detection applications
AbstractYou only look once (YOLO) is being used as the most popular object detection software in many intelligent video applications due to its ease of use and high object detection precision. In addition, in recent years, various intelligent vision ...
Comments
Information & Contributors
Information
Published In
September 2023
1540 pages
ISBN:9798400707674
DOI:10.1145/3641584
Copyright © 2023 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: 14 June 2024
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Funding Sources
- Central University Graduate Education and Teaching Reform Project
- The National Key Research and Development Program of China
- Fundamental Research Funds for the Central Universities
Conference
AIPR 2023
AIPR 2023: 2023 6th International Conference on Artificial Intelligence and Pattern Recognition
September 22 - 24, 2023
Xiamen, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 28Total Downloads
- Downloads (Last 12 months)28
- Downloads (Last 6 weeks)12
Reflects downloads up to 22 Sep 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