Abstract
In many real-world datasets, like WebVision, the performance of DNN based classifier is often limited by the noisy labeled data. To tackle this problem, some image related side information, such as captions and tags, often reveal underlying relationships across images. In this paper, we present an efficient weakly-supervised learning by using a Side Information Network (SINet), which aims to effectively carry out a large scale classification with severely noisy labels. The proposed SINet consists of a visual prototype module and a noise weighting module. The visual prototype module is designed to generate a compact representation for each category by introducing the side information. The noise weighting module aims to estimate the correctness of each noisy image and produce a confidence score for image ranking during the training procedure. The propsed SINet can largely alleviate the negative impact of noisy image labels, and is beneficial to train a high performance CNN based classifier. Besides, we released a fine-grained product dataset called AliProducts, which contains more than 2.5 million noisy web images crawled from the internet by using queries generated from 50,000 fine-grained semantic classes. Extensive experiments on several popular benchmarks (i.e. Webvision, ImageNet and Clothing-1M) and our proposed AliProducts achieve state-of-the-art performance. The SINet has won the first place in the 5000 category classification task on WebVision Challenge 2019, and outperforms other competitors by a large margin.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Deng, J., Dong, W., Socher, R., Li, J., Li, K., Li, F.: Imagenet: a large-scale hierarchical image database. In: CVPR (2009)
Nettleton, D., Orriols, P., Fornells, A.: A study of the effect of different types of noise on the precision of supervised learning techniques. Artif. Intell. Rev. 33(4), 275–306 (2010)
Pechenizkiy, M., Tsymbal, A., Puuronen, S., Pechenizkiy, O.: Class noise and supervised learning in medical domains: the effect of feature extraction. In: IEEE Symposium on Computer-Based Medical Systems (CBMS), pp. 708–713 (2006)
Brooks, J.: Support vector machines with the ramp loss and the hard margin loss. Oper. Res. 59(2), 467–479 (2011)
Ghosh, A., Kumar, H., Sastry, P.: Robust loss functions under label noise for deep neural networks. In: AAAI (2017)
Ghosh, A., Manwani, N., Sastry, P.: Making risk minimization tolerant to label noise. Neurocomputing 160, 93–107 (2015)
Shirazi, H., Vasconcelos, N.: On the design of loss functions for classification: theory, robustness to outliers, and savageboost. In: NeurIPS (2009)
Rooyen, B., Menon, A., CWilliamson, R.: Learning with symmetric label noise: the importance of being unhinged. In: NeurIPS (2015)
Zhang, Z., Sabuncu, M.: Generalized cross entropy loss for training deep neural networks with noisy labels. In: NeurIPS (2018)
Jiang, L., Zhou, Z., Leung, T., Li, T., Li, F.: Mentornet: regularizing very deep neural networks on corrupted labels. arXiv preprint arXiv:1712.05055 (2017)
Lee, K., He, X., Zhang, L., Yang, L.: Cleannet: transfer learning for scalable image classifier training with label noise. arXiv preprint arXiv:1711.07131 (2017)
Ren, M., Zeng, W., Yang, B., Urtasun, R.: Learning to reweight examples for robust deep learning. arXiv preprint arXiv:1803.09050 (2018)
Wang, Y., et al.: Iterative learning with open-set noisy labels. In: CVPR (2018)
Xue, C., Dou, Q., Shi, X., Chen, H., Heng, P.: Robust learning at noisy labeled medical images: applied to skin lesion classification. arxiv.org (2019)
Kriegel, H., Kroger, P., Schubert, E., Zimek, A.: Loop: local outlier probabilities. In: CIKM (2009)
Guo, S., et al.: CurriculumNet: weakly supervised learning from large-scale web images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 139–154. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01249-6_9
Reed, S., Lee, H., Anguelov, D., Szegedy, C., Erhan, D., Rabinovich, A.: Training deep neural networks on noisy labels with bootstrapping. arXiv preprint arXiv:1412.6596 (2014)
Tanaka, D., Ikami, D., Yamasaki, T., Aizawa, K.: Joint optimization framework for learning with noisy labels. In: CVPR (2018)
Li, J., Wong, Y., Zhao, Q., Kankanhalli, M.: Learning to learn from noisy labeled data. In: CVPR (2019)
Han, J., Luo, P., Wang, X.: Deep self-learning from noisy labels. arXiv preprint arXiv:1908.02160 (2019)
Zhang, W., Wang, Y., Qiao, Y.: MetaCleaner: learning to hallucinate clean representations for noisy-labeled visual recognition. In: CVPR (2019)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Zhu, X., Wu, X.: Class noise vs attribute noise: a quantitative study. Artif. Intell. Rev. 22(3), 177–210 (2004)
Simonyan K., Zisserman A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)
Szegedy, C., et al.: Going deeper with convolutions. arXiv:1409.4842 (2014)
Sukhbaatar, S., Bruna, J., Paluri, M., Bourdev, L., Fergus, R.: Training convolutional networks with noisy labels. arXiv preprint arXiv:1406.2080 (2014)
Goldberger, J., Reuven, E.: Training deep neural-networks using a noise adaptation layer. In: ICLR (2017)
Patrini, G., Rozza, A., Menon, A., Nock, R., Qu, L.: Making deep neural networks robust to label noise: a loss correction approach. In: CVPR (2017)
Hendrycks, D., Mazeika, M., Wilson, D., Gimpel, K.: Using trusted data to train deep networks on labels corrupted by severe noise. In: NeurIPS (2018)
Zhang Z., Sabuncu, M.: Generalized cross entropy loss for training deep neural networks with noisy labels. In: NeurIPS (2018)
Li, Y., Yang, J., Song, Y., Cao, L., Luo, J., Li, L.: Learning from noisy labels with distillation. In: CVPR (2017)
Veit, A., Alldrin, N., Chechik, G., Krasin, I., Gupta, A., Belongie, S.: Learning from noisy large-scale datasets with minimal supervision. In: CVPR (2017)
Brodley, C., Friedl, M.: Identifying mislabeled training data. arXiv:1106.0219 (2011)
Miranda, A., Garcia, L., Carvalho A., Lorena, A.: Use of classification algorithms in noise detection and elimination. In: HAIS (2009)
Barandela, R., Gasca, E.: Decontamination of training samples for supervised pattern recognition methods. In: ICAPR (2000)
Xiao, T., Xia, T., Yang, Y., Huang, C., Wang, X.: Learning from massive noisy labeled data for image classification. In: CVPR (2015)
Li, W., Wang, L., Li, W., Agustsson, E., Gool, L.: Webvision database: visual learning and understanding from web data. CoRR abs/1708.02862 (2017)
Alexander, B., Denzler, J.: Not just a matter of semantics: the relationship between visual and semantic similarity. In: German Conference on Pattern Recognition (2019)
Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: ACL (2019)
Miller, G.A.: WordNet: a lexical database for English. Commun. ACM 38(11), 39–41 (1995)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Cheng, L. et al. (2020). Weakly Supervised Learning with Side Information for Noisy Labeled Images. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12375. Springer, Cham. https://doi.org/10.1007/978-3-030-58577-8_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-58577-8_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58576-1
Online ISBN: 978-3-030-58577-8
eBook Packages: Computer ScienceComputer Science (R0)