제한된 레이블 데이터에 대한 Mean Teacher 반지도학습을 활용한 견고한 포트홀 이미지 분류
Utilizing Mean Teacher Semi-Supervised Learning for Robust Pothole Image Classification
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
포장도로에서 발생하는 포트홀은 고속 주행 차량에 치명적인 영향을 미치며, 사망사고를 유발할수 있는 도로상의 장애물이다. 이를 방지하기 위해 일반적으로는 작업자가 직접 포트홀을 탐지하는방식을 사용해왔으나, 이는 작업자의 안전 문제와 예측하기 어려운 범주에서 발생하는 모든 포트홀을 인력으로 탐지하는 것이 비효율적이기 때문에 한계가 있다. 또한, 도로 환경과 관련된 지반 환경이 포트홀 생성에 영향을 미치기 때문에, 완벽한 포트홀 방지는 어렵다. 데이터셋 구축을 위해서는전문가의 지도하에 라벨링 작업이 필요하지만, 이는 매우 시간과 비용이 많이 필요하다. 따라서, 본논문에서는 Mean Teacher 기법을 사용하여 라벨링된 데이터의 샘플 수가 적더라도 지도학습보다 더욱 강인한 포트홀 이미지 분류 성능을 보여준다. 이러한 결과는 성능지표와 GradCAM을 통해 입증되었으며, 준지도학습을 사용할 때 15개의 사전 학습된 CNN 모델이 평균 90.41%의 정확도를 달성하며, 지도학습과 비교하여 2%에서 9%의 차이로 강인한 성능을 나타내는 것을 확인하였다.
Abstract
Potholes that occur on paved roads can have fatal consequences for vehicles traveling at high speeds and may even lead to fatalities. While manual detection of potholes using human labor is commonly used to prevent pothole-related accidents, it is economically and temporally inefficient due to the exposure of workers on the road and the difficulty in predicting potholes in certain categories. Therefore, completely preventing potholes is nearly impossible, and even preventing their formation is limited due to the influence of ground conditions closely related to road environments. Additionally, labeling work guided by experts is required for dataset construction. Thus, in this paper, we utilized the Mean Teacher technique, one of the semi-supervised learning-based knowledge distillation methods, to achieve robust performance in pothole image classification even with limited labeled data. We demonstrated this using performance metrics and GradCAM, showing that when using semi-supervised learning, 15 pre-trained CNN models achieved an average accuracy of 90.41%, with a minimum of 2% and a maximum of 9% performance difference compared to supervised learning.
참고문헌 (22)
- A. Tarvainen, "Mean Teachers Are Better Role Models:Weight-Averaged Consistency Targets Improve Semi-Supervised Deep Learning Results" (2017), Advances in Neural Information Processing System (NIPS 2017)
- R. R. Selvaraju, "Grad-CAM: Visual Explanations from Deep Networks Via Gradient-Based Localization", Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp.618~626 (2017)
- K. K. Vupparaboina, "Laser-Based Detection and Depth Estimation of Dry and Water-Filled Potholes: A Geometric Approach", Twenty First National Conference on Communications (NCC), pp.1~6 (2015)
- X. Yu, "Pavement Pothole Detection And Severity Measurement Using Laser Imaging", IEEE International Conference on Electro, 2011, 1~5
- S. Nienaber, "Detecting Potholes Using Simple Image Processing Techniques and Real-World Footage", Proceedings of the 34th Southern African Transport Conference (SATC 2015), pp.6~9 (2015)
- K. Vigneshwar, "Detection and Counting of Pothole Using Image Processing Techniques", IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), pp.1~4 (2016)
- M. H. Asad, "Pothole Detection Using Deep Learning: A Real-Time and AI-on-the-Edge Perspective", Advances in Civil Engineering (2022)
- N. Çınar, "An automated pothole detection via transfer learning", 2022 International Conference on Decision Aid Sciences and Applications (DASA), pp.1355~1358 (2022)
- I. K. Kim, "Pothole Detection Method based on an Ensemble of Pretrained Deep Learning Models", 2022 Korean Society for Internet Information (KSII) SPRING Conference (2022)
- A. Krizhevsky, "ImageNet Classification with Deep Convolutional Neural Networks", Proceedings of the 25th International Conference on Neural Information Processing Systems(NIPS), 60(6), pp.84~90 (2017)
- G. Huang, "Densely Connected Convolutional Networks", Proceedings of the IEEE conference on computer vision and pattern recognition(CVPR), pp.4700~4708 (2017)
- M. Tan, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks", International conference on machine learning(ICML), pp.6105~6114 (2019)
- C. Szegedy, "Rethinking the Inception Architecture for Computer Vision", 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.2818~2826 (2016)
- M. Tan, "MnasNet : Platform-Aware Neural Architecture Search for Mobile", Proceedings of the IEEE, 2019, 2820~2828
- Jing Xu, "RegNet: Self-Regulated Network for Image Classification", IEEE Transactions on Neural Networks and Learning Systems, 34(11), pp.1~6 (2022), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- K. He, "Deep Residual Learning for Image Recognition", 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.770~778 (2016)
- S. Xie, "Aggregated Residual Transformations for Deep Neural Networks", Proceddings of the IEEE conference on computer vision and pattern recognition(CVPR), pp.1492~1500 (2017)
- X. Zhang, "ShuffleNet: An Extremely Efficient Convolutional Nerual Network for Mobile Devices", Proceddings of the IEE conference on computer vision and pattern recognition(CVPR), pp.6848~6856 (2018)