Abstract
In the area of image recognition, the quality of image label data has a significant impact on the performance of classification models. Therefore, manual annotation has been used as a means to label images. However, manual annotation is laborious and time-consuming and can introduce additional noise. To address these issues, this paper investigates an automatic algorithm for improving a cat breed classification model based on meta loss correction. The proposed algorithm leverages web crawling techniques to obtain unlabeled images of cats, filters them through object recognition, and selects only images containing cats. These images are then fed into the algorithm, which utilizes a pretrained initial model to generate pseudo-labels. These pseudo-labeled data are subsequently refined using a meta loss function, correcting the inaccuracies associated with the pseudo-labels. Finally, the labeled new data is merged with the original dataset, gradually increasing both the quantity and quality of the dataset. Experimental results demonstrate that as the merged dataset expands, the model’s error decreases gradually, and its performance improves.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Wang, Z., Hu, G., Hu, Q.: Training noise-robust deep neural networks via meta-learning. In: CVPR, pp. 4523–4532 (2020)
Deng, W., Zheng, L.: Are labels always necessary for classifier accuracy evaluation? In: CVPR, pp. 15064–15073 (2021)
Guo, X., Yang, C., Li, B., Yuan, Y.: MetaCorrection: domain-aware meta loss correction for unsupervised domain adaptation in semantic segmentation. In: CVPR, pp. 3926–3935 (2021)
Algan, G., Ulusoy, I.: MetaLabelNet: learning to generate soft-labels from noisy-labels. IEEE Trans. Image Process. 31, 4352–4362 (2022)
Zheng, G., Awadallah, A.H., Dumais, S.: Meta label correction for noisy label learning. arXiv e-prints arXiv1911.03809 (2019)
Algan, G., Ulusoy, I.: Image classification with deep learning in the presence of noisy labels: a survey. arXiv preprint arXiv:1912.05170 (2019)
Shu, J., Zhao, Q., Xu, Z., Meng, D.: Meta transition adaptation for robust deep learning with noisy labels. arXiv preprint arXiv:2006.05697 (2020)
Mao, J., Yu, Q., Yamakata, Y., Aizawa, K.: Noisy annotation refinement for object detection. arXiv preprint arXiv:2110.1045 (2021)
Wei, C., Shen, K., Chen, Y., Ma, T.: Theoretical analysis of self-training with deep networks on unlabeled data. arXiv preprint arXiv:2010.03622 (2020)
Wang, P., Peng, J., Pedersoli, M., Zhou, Y., Zhang, C., Desrosiers, C.: Self-paced and self-consistent co-training for semi-supervised image segmentation. arXiv preprint arXiv:2011.0032 (2020)
Xie, Q., Luong, M. -T., Hovy, E., Le, Q.V.: Self-training with noisy student improves imagenet classification. In: CVPR, pp. 10684–10695 (2020)
Feurer, M., Eggensperger, K., Falkner, S., Lindauer, M., Hutter, F.: Auto-Sklearn 2.0: hands-free AutoML via meta-learning. arXiv preprint arXiv:2007.04074 (2020)
Kye, S. M., Lee, H. B., Kim, H., Hwang, S.J.: Meta-learned confidence for few-shot learning. arXiv preprint arXiv:2002.12017 (2020)
Yi, L., Liu, S., She, Q., McLeod, A.I., Wang, B.: On learning contrastive representations for learning with noisy labels. arXiv preprint arXiv:2203.01785 (2022)
Zhang, Y., Zheng, S., Wu, P., Goswami, M., Chen, C.: Learning with feature-dependent label noise: a progressive approach. arXiv preprint arXiv:2103.07756 (2021)
Chew, R., Wenger, M., Kery, C., Nance, J., Richards, K., Hadley, E., Baumgartner, P.: SMART: an open source data labeling platform for supervised learning. arXiv preprint arXiv:1812.06591 (2018)
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
Khaodee, N., Rao, W., Qiao, H., Su, S. (2024). Enhancement of Cat Breeds Classification Model Based on Meta Loss Correction. In: Sun, Y., Lu, T., Wang, T., Fan, H., Liu, D., Du, B. (eds) Computer Supported Cooperative Work and Social Computing. ChineseCSCW 2023. Communications in Computer and Information Science, vol 2013. Springer, Singapore. https://doi.org/10.1007/978-981-99-9640-7_8
Download citation
DOI: https://doi.org/10.1007/978-981-99-9640-7_8
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-9639-1
Online ISBN: 978-981-99-9640-7
eBook Packages: Computer ScienceComputer Science (R0)
