Abstract
Car damage segmentation, an integral part of vehicle damage assessment, involves identifying and classifying various types of damages from images of vehicles, thereby enhancing the efficiency and accuracy of assessment processes. This paper introduces an efficient approach for car damage assessment by combining pseudo-labeling and deep learning techniques. The method addresses the challenge of limited labeled data in car damage segmentation by leveraging unlabeled data. Pseudo-labels are generated using a deep spectral approach and refined through merge and flip-bit operations. Two models, i.e., Mask R-CNN and SegFormer, are trained using a combination of ground truth labels and pseudo-labels. Experimental evaluation of the CarDD dataset demonstrates the superior accuracy of our method, achieving improvements of 12.9% in instance segmentation and 18.8% in semantic segmentation when utilizing a 1/2 ground truth ratio. In addition to enhanced accuracy, our approach offers several benefits, including time savings, cost reductions, and the elimination of biases associated with human judgment. By enabling more precise and reliable identification of car damages, our method enhances the overall effectiveness of the assessment process. The integration of pseudo-labeling and deep learning techniques in car damage assessment holds significant potential for improving efficiency and accuracy in real-world scenarios.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Balasubramanian, R., Libarikian, A., McElhaney, D.: Insurance 2030–the impact of AI on the future of insurance. McKinsey & Company (2018)
Berthelot, D., Carlini, N., Goodfellow, I.J., Papernot, N., Oliver, A., Raffel, C.: MixMatch: a holistic approach to semi-supervised learning. In: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, pp. 5050–5060 (2019)
Chen, Q., et al.: A deep neural network inverse solution to recover pre-crash impact data of car collisions. Transp. Res. Part C Emerg. Technol. 126, 103009 (2021)
Gansbeke, W.V., Vandenhende, S., Georgoulis, S., Gool, L.V.: Unsupervised semantic segmentation by contrasting object mask proposals. In: 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021, pp. 10032–10042 (2021)
He, K., Gkioxari, G., Dollár, P., Girshick, R.B.: Mask R-CNN. In: IEEE International Conference on Computer Vision, ICCV 2017, pp. 2980–2988 (2017)
Kyu, P.M., Woraratpanya, K.: Car damage detection and classification. In: The 11th International Conference on Advances in Information Technology, IAIT 2020 (2020)
Lee, D.H.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning, International Conference on Machine Learning Workshop 2013, pp. 1–6 (2013)
Lee, J., Yi, J., Shin, C., Yoon, S.: BBAM: bounding box attribution map for weakly supervised semantic and instance segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, pp. 2643–2652 (2021)
Melas-Kyriazi, L., Rupprecht, C., Laina, I., Vedaldi, A.: Deep spectral methods: a surprisingly strong baseline for unsupervised semantic segmentation and localization. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, pp. 8354–8365 (2022)
Pal, N., Arora, P., Kohli, P., Sundararaman, D., Palakurthy, S.S.: How much is my car worth? A methodology for predicting used cars’ prices using random forest. In: The 2018 Future of Information and Communication Conference, FICC 2018, pp. 413–422 (2019)
Patil, K., Kulkarni, M., Sriraman, A., Karande, S.: Deep learning based car damage classification. In: 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017, pp. 50–54 (2017)
Shaikh, M.K., Zaki, H., Tahir, M., Khan, M.A., Siddiqui, O.A., Rahim, I.U.: The framework of car price prediction and damage detection technique. Pak. J. Eng. Technol. 5(4), 52–59 (2022)
Sohn, K., et al.: FixMatch: simplifying semi-supervised learning with consistency and confidence. In: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020 (2020)
Wang, X., Li, W., Wu, Z.: CarDD: a new dataset for vision-based car damage detection. IEEE Trans. Intell. Transp. Syst. 24(7), 7202–7214 (2023)
Wang, Y., et al.: Semi-supervised semantic segmentation using unreliable pseudo-labels. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, pp. 4238–4247 (2022)
Xie, E., Wang, W., Yu, Z., Anandkumar, A., Álvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. In: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, pp. 12077–12090 (2021)
Yang, L., Qi, L., Feng, L., Zhang, W., Shi, Y.: Revisiting weak-to-strong consistency in semi-supervised semantic segmentation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, pp. 7236–7246 (2023)
Zhang, W., et al.: Automatic car damage assessment system: reading and understanding videos as professional insurance inspectors. In: The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, pp. 13646–13647 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Taspan, N., Madthing, B., Chetprayoon, P., Angsarawanee, T., Pasupa, K., Sakdejayont, T. (2024). Generating Pseudo-labels for Car Damage Segmentation Using Deep Spectral Method. In: Luo, B., Cheng, L., Wu, ZG., Li, H., Li, C. (eds) Neural Information Processing. ICONIP 2023. Communications in Computer and Information Science, vol 1969. Springer, Singapore. https://doi.org/10.1007/978-981-99-8184-7_36
Download citation
DOI: https://doi.org/10.1007/978-981-99-8184-7_36
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8183-0
Online ISBN: 978-981-99-8184-7
eBook Packages: Computer ScienceComputer Science (R0)