Analysis of EfficientNet-B0 with Sample Reweighting and Early-Learning Regularization for Food Recognition under Label Noise

Danang Danang; Toni Wijanarko Adi Putra

doi:10.55606/jcsr-politama.v3i6.6154

Authors

Danang Danang Universitas Sains dan Teknologi Komputer
Toni Wijanarko Adi Putra Universitas Sains dan Teknologi Komputer

DOI:

https://doi.org/10.55606/jcsr-politama.v3i6.6154

Keywords:

Efficientnet-B0, Food Recognition, Label Noise, Probability Calibration, Sample Reweighting

Abstract

Food recognition systems are commonly developed under the assumption that training labels are fully accurate. In real-world applications, however, food image datasets frequently contain noisy annotations caused by incorrect user inputs, weak labeling mechanisms, or automated data collection processes. This study investigates the robustness of supervised food recognition under synthetic label noise using the Food-101 dataset Food-101. The research employs EfficientNet-B0 as a computationally efficient backbone model and compares conventional cross-entropy learning with a robust training approach that integrates two mechanisms: (1) small-loss sample reweighting to reduce the influence of potentially corrupted samples, and (2) an early-learning stopping strategy based on the memorization gap between noisy training accuracy and clean validation accuracy. Symmetric label noise levels of 20% and 40% are introduced only into the training data, while validation and testing datasets remain unaffected. Experimental results on a 20-class subset demonstrate that the proposed approach substantially improves clean test accuracy from 0.6476 to 0.8176 under 20% noise and from 0.5636 to 0.6928 under 40% noise. In addition, probability calibration performance measured by Expected Calibration Error (ECE) is improved from 0.1474 to 0.0813 at the 40% noise setting. Additional experiments on the complete 101-class dataset also reveal consistent performance improvements despite shorter training durations. The findings suggest that combining loss-aware sample weighting with memorization-aware early stopping can provide an efficient and practical solution for building robust and reliable food recognition models in noisy-label environments.

Downloads

Download data is not yet available.

References

Arazo, E., Ortenzi, F., Albert, P., O'Connor, N. E., & McGuinness, K. (2019). Unsupervised label noise modeling and loss correction. In Proceedings of the International Conference on Machine Learning (ICML).

Arpit, D., Jastrzebski, S., Ballas, N., Krueger, D., Bengio, E., Kanwal, M. S., et al. (2017). A closer look at memorization in deep networks. In Proceedings of the International Conference on Machine Learning (ICML).

Bossard, L., Guillaumin, M., & Van Gool, L. (2014). Food-101: Mining discriminative components with random forests. In European Conference on Computer Vision (ECCV) (pp. 446–461). https://doi.org/10.1007/978-3-319-10599-4_29

Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017). On calibration of modern neural networks. In Proceedings of the International Conference on Machine Learning (ICML).

Han, B., Yao, Q., Yu, X., Niu, G., Xu, M., Hu, W., Tsang, I. W., & Sugiyama, M. (2018). Co-teaching: Robust training of deep neural networks with extremely noisy labels. In Advances in Neural Information Processing Systems (NeurIPS).

He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR.2016.90

Hendrycks, D., & Dietterich, T. (2019). Benchmarking neural network robustness to common corruptions and perturbations. In Proceedings of the International Conference on Learning Representations (ICLR).

Jiang, L., Zhou, Z., Leung, T., Li, L.-J., & Fei-Fei, L. (2018). MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels. In Proceedings of the International Conference on Machine Learning (ICML).

Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In Proceedings of the International Conference on Learning Representations (ICLR).

Kuleshov, V., Fenner, N., & Ermon, S. (2018). Accurate uncertainties for deep learning using calibrated regression. In Proceedings of the International Conference on Machine Learning (ICML).

Lhoest, Q., Villanova del Moral, A., Jernite, Y., Thakur, A., von Platen, P., Patil, S., et al. (2021). Datasets: A community library for natural language processing. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP) (pp. 175–184). https://doi.org/10.18653/v1/2021.emnlp-demo.21

Li, J., Socher, R., & Hoi, S. C. H. (2020). DivideMix: Learning with noisy labels as semi-supervised learning. In Proceedings of the International Conference on Learning Representations (ICLR).

Liu, S., Niu, G., & Sugiyama, M. (2020). Early-learning regularization prevents memorization of noisy labels. In Advances in Neural Information Processing Systems (NeurIPS).

Loshchilov, I., & Hutter, F. (2019). Decoupled weight decay regularization. In Proceedings of the International Conference on Learning Representations (ICLR).

Müller, R., Kornblith, S., & Hinton, G. (2019). When does label smoothing help? In Advances in Neural Information Processing Systems (NeurIPS).

Naeini, M. P., Cooper, G., & Hauskrecht, M. (2015). Obtaining well-calibrated probabilities using Bayesian binning. In Proceedings of the AAAI Conference on Artificial Intelligence.

Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., et al. (2019). PyTorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems (NeurIPS).

Patrini, G., Rozza, A., Menon, A. K., Nock, R., & Qu, L. (2017). Making deep neural networks robust to label noise: A loss correction approach. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1944–1952). https://doi.org/10.1109/CVPR.2017.240

Ren, M., Zeng, W., Yang, B., & Urtasun, R. (2018). Learning to reweight examples for robust deep learning. In Proceedings of the International Conference on Machine Learning (ICML).

Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., et al. (2015). ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211–252. https://doi.org/10.1007/s11263-015-0816-y

Song, H., Kim, M., Park, D., Shin, Y., Lee, J.-G., et al. (2022). Learning from noisy labels: A survey. IEEE Transactions on Neural Networks and Learning Systems.

Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR.2016.308

Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the International Conference on Machine Learning (ICML) (pp. 6105–6114).

Thulasidasan, S., Bhattacharya, T., Bilmes, J. A., Chennupati, G., & Mohd-Yusof, J. (2019). Combating label noise in deep learning using abstention. In Proceedings of the International Conference on Machine Learning (ICML).

Zhang, Z., & Sabuncu, M. R. (2018). Generalized cross entropy loss for training deep neural networks with noisy labels. In Advances in Neural Information Processing Systems (NeurIPS).