Sewer-MoE: A tuned Mixture of Experts Model for Sewer Defect Classification
Article No.: 48, Pages 1 - 5
Abstract
Abstract: Inspection of pipelines is particularly important for the drainage industry, and automation of this process has received a lot of attention. We propose the Mixture of Experts for Sewer Defect Classification (Sewer-MoE), an innovative model for identifying pipe defects, in which we train multiple expert models and then merge them into a single multiclassification model. During the model training process, we produced an attention mechanism structure that allows each expert model to refer to the other expert models, while weighting each classification to emphasise the defect types with fewer occurrences, effectively improving the prediction accuracy. We evaluate our Mixture of Experts for Sewer Defect Classification (Sewer-MoE) on the Sewer-ML dataset, where we use our model to compare the model proposed by Xie et al. and the model proposed by Chen et al. with the original model after modifying them, and our model significantly outperforms the original model on the same size dataset.
References
[1]
Yan X, Song X. An Image Recognition Algorithm for Defect Detection of Underground Pipelines Based on Convolutional Neural Network[J]. Traitement du Signal, 2020, 37(1).
[2]
Wang M, Kumar S S, Cheng J C P. Automated sewer pipe defect tracking in CCTV videos based on defect detection and metric learning[J]. Automation in Construction, 2021, 121: 103438.
[3]
Li W, Liu G, Zeng C. Research on Drainage pipe defect detection Method based on case segmentation+ CCTV [J][J]. Electronic Measurement Technique, 2022, 3: 045.
[4]
Xie Q, Li D, Xu J, Automatic detection and classification of sewer defects via hierarchical deep learning[J]. IEEE Transactions on Automation Science and Engineering, 2019, 16(4): 1836-1847.
[5]
Shazeer N, Mirhoseini A, Maziarz K, Outrageously large neural networks: The sparsely-gated mixture-of-experts layer[J]. arXiv preprint arXiv:1701.06538, 2017.
[6]
Chen K, Hu H, Chen C, An intelligent sewer defect detection method based on convolutional neural network[C]//2018 IEEE International conference on information and automation (ICIA). IEEE, 2018: 1301-1306.
[7]
Haurum J B, Moeslund T B. Sewer-ML: A multi-label sewer defect classification dataset and benchmark[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 13456-13467.
[8]
Powers D M W. Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation[J]. arXiv preprint arXiv:2010.16061, 2020.
[9]
Rijsbergen V. Information retrieval; Butterworth, 1978[J]. J. librariansh., 1979, 11: 237.
[10]
Jacobs R A, Jordan M I, Nowlan S J, Adaptive mixtures of local experts[J]. Neural computation, 1991, 3(1): 79-87.
[11]
Shazeer N, Mirhoseini A, Maziarz K, Outrageously large neural networks: The sparsely-gated mixture-of-experts layer[J]. arXiv preprint arXiv:1701.06538, 2017.
[12]
Lepikhin D, Lee H J, Xu Y, Gshard: Scaling giant models with conditional computation and automatic sharding[J]. arXiv preprint arXiv:2006.16668, 2020.
[13]
Fedus W, Zoph B, Shazeer N. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity[J]. The Journal of Machine Learning Research, 2022, 23(1): 5232-5270.
[14]
Xue F, Shi Z, Wei F, Go wider instead of deeper[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2022, 36(8): 8779-8787.
[15]
Du N, Huang Y, Dai A M, Glam: Efficient scaling of language models with mixture-of-experts[C]//International Conference on Machine Learning. PMLR, 2022: 5547-5569.
[16]
Zuo S, Zhang Q, Liang C, Moebert: from bert to mixture-of-experts via importance-guided adaptation[J]. arXiv preprint arXiv:2204.07675, 2022.
[17]
Szegedy C, Vanhoucke V, Ioffe S, Rethinking the inception architecture for computer vision[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 2818-2826.
[18]
L. Yan, "Video Captioning Using Global-Local Representation," in IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 10, pp. 6642-6656, Oct. 2022.
[19]
L. Yan, Q. Wang, S. Ma, J. Wang and C. Yu, "Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework With Spatio-Temporal Collaboration," in IEEE Transactions on Circuits and Systems for Video Technology, vol. 33, no. 1, pp. 393-406, Jan. 2023.
Recommendations
Mixture of experts classification using a hierarchical mixture model
A three-level hierarchical mixture model for classification is presented that models the following data generation process: (1) the data are generated by a finite number of sources (clusters), and (2) the generation mechanism of each source assumes the ...
The Study of Treating Municipal Sewage by Using Sewer Networks
CDCIEM '11: Proceedings of the 2011 International Conference on Computer Distributed Control and Intelligent Environmental MonitoringWhen wastewater is collected and deliver to sewage treatment plant in sewer network, there are occurring complicate process about physical chemical and biological. It has great impact to organic removal and transformation efficiency where happened ...
Quadratically gated mixture of experts for incomplete data classification
ICML '07: Proceedings of the 24th international conference on Machine learningWe introduce quadratically gated mixture of experts (QGME), a statistical model for multi-class nonlinear classification. The QGME is formulated in the setting of incomplete data, where the data values are partially observed. We show that the missing ...
Comments
Information & Contributors
Information
Published In
January 2024
506 pages
ISBN:9798400718199
DOI:10.1145/3653804
Copyright © 2024 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: 01 June 2024
Check for updates
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
CVDL 2024
CVDL 2024: The International Conference on Computer Vision and Deep Learning
January 19 - 21, 2024
Changsha, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 35Total Downloads
- Downloads (Last 12 months)35
- Downloads (Last 6 weeks)2
Reflects downloads up to 18 Feb 2025
Other Metrics
Citations
View Options
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