Abstract
In this work, we develop a new approach for learning a deep neural network for image classification with noisy labels using ensemble diversified learning. We first partition the training set into multiple subsets with diversified image characteristics. For each subset, we train a separate deep neural network image classifier. These networks are then used to encode the input image into different feature vectors, providing diversified observations of the input image. The encoded features are then fused together and further analyzed by a decision network to produce the final classification output. We study image classification on noisy labels with and without the access to clean samples. Our extensive experimental results on the CIFAR-10 and MNIST datasets demonstrate that our proposed method outperforms existing methods by a large margin.
Similar content being viewed by others
References
Ahmed A, Yousif H, Kays R, He Z (2020) Animal species classification using deep neural networks with noise labels. Eco Inform 57:101063
Azadi S, Feng J, Jegelka S, Darrell T (2015) Auxiliary image regularization for deep cnns with noisy labels. arXiv preprint arXiv:1511.07069
Barandela R, Gasca E (2000) Decontamination of training samples for supervised pattern recognition methods. In: Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR). Springer, Berlin, Heidelberg, pp 621–630
Beigman E, Klebanov BB (2009) Learning with annotation noise. In: Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, pp 280–287
Brodley CE, Friedl MA (1999) Identifying mislabeled training data. J Artif Intell Res 11:131–167
Chu J, Guo Z, Leng L (2018) Object detection based on multi-layer convolution feature fusion and online hard example mining. IEEE Access 6:19959–19967
Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp 248–255. IEEE, Piscataway
Ding Y, Wang L, Fan D, Gong B (2018) A semi-supervised two-stage approach to learning from noisy labels. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, Piscataway, pp 1215–1224
Fawzi A, Moosavi-Dezfooli SM, Frossard P (2017) The robustness of deep networks: A geometrical perspective. IEEE Signal Process Mag 34(6):50–62
Fergus R, Fei-Fei L, Perona P, Zisserman A (2010) Learning object categories from internet image searches. Proc IEEE 98(8):1453-66
Ghosh A, Manwani N, Sastry PS (2015) Making risk minimization tolerant to label noise. Neurocomputing 160:93–107
Han B, Yao Q, Yu X, Niu G, Xu M, Hu W, Tsang I, Sugiyama M (2018) Co-teaching: Robust training of deep neural networks with extremely noisy labels. Adv Neural Inf Proces Syst 31:8527–8537
Han B, Niu G, Yao J, Yu X, Xu M, Tsang I, Sugiyama M (2018) Pumpout: A meta approach to robust deep learning with noisy labels. arXiv preprint arXiv:1809.11008.
Hendrycks D, Mazeika M, Wilson D, Gimpel K (2018) Using trusted data to train deep networks on labels corrupted by severe noise. In: Advances in neural information processing systems, pp 10456–10465
Hinton G, Deng L, Yu D, Dahl GE, Mohamed AR, Jaitly N, Senior A, Vanhoucke V, Nguyen P, Sainath TN, Kingsbury B (2012) Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Process Mag 29(6):82–97
Jiang L, Zhou Z, Leung T, Li LJ, Fei-Fei L (2018) Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels. In: International Conference on Machine Learning, pp 2304–2313. PMLR.
Jindal I, Nokleby M, Chen X (2016) Learning deep networks from noisy labels with dropout regularization. In: 2016 IEEE 16th International Conference on Data Mining (ICDM). IEEE, Piscataway, pp 967–972
Krizhevsky A, Hinton G (2009) Learning multiple layers of features from tiny images
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems
LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–324
Lee KH, He X, Zhang L, Yang L (2018) Cleannet: Transfer learning for scalable image classifier training with label noise. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5447–5456
Leng L, Zhang J (2011) Dual-key-binding cancelable palmprint cryptosystem for palmprint protection and information security. J Netw Comput Appl 34(6):1979–1989
Leng L, Zhang J (2013) Palmhash code vs. palmphasor code. Neurocomputing 108:1–12
Leng L, Zhang J, Chen G, Khan MK, Bai P (2011) Two dimensional PalmPhasor enhanced by multi-orientation score level fusion. In: FTRA International Conference on Secure and Trust Computing, Data Management, and Application. Springer, Berlin, Heidelberg, pp 122–129
Leng L, Li M, Teoh AB (2013) Conjugate 2DPalmHash code for secure palm-print-vein verification. In: 2013 6th International Congress on Image and Signal Processing (CISP), vol 3. IEEE, Piscataway, pp 1705–1710
Leng L, Teoh AB, Li M, Khan MK (2014) A remote cancelable palmprint authentication protocol based on multi-directional two‐dimensional PalmPhasor‐fusion. Secur Commun Netw 7(11):1860–1871
Leng L, Li M, Kim C, Bi X (2017) Dual-source discrimination power analysis for multi-instance contactless palmprint recognition. Multimed Tools Appl 76(1):333–354
Li Y, Yang J, Song Y, Cao L, Luo J, Li LJ (2017) Learning from noisy labels with distillation. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1910–1918
Li J, Wong Y, Zhao Q, Kankanhalli MS (2019) Learning to learn from noisy labeled data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5051–5059
Manwani N, Sastry PS (2013) Noise tolerance under risk minimization. IEEE Trans Cybern 43(3):1146–1151
Masnadi-Shirazi H, Vasconcelos N (2008) On the design of loss functions for classification: theory, robustness to outliers, and savageboost. Adv Neural Inf Proces Syst 21:1049–1056
Miranda AL, Garcia LP, Carvalho AC, Lorena AC (2009) Use of classification algorithms in noise detection and elimination. In: International Conference on Hybrid Artificial Intelligence Systems. Springer, Berlin, Heidelberg, pp 417–424
Nettleton DF, Orriols-Puig A, Fornells A (2010) A study of the effect of different types of noise on the precision of supervised learning techniques. Artif Intell Rev 33(4):275–306
Niu L, Li W, Xu D (2015) Visual recognition by learning from web data: A weakly supervised domain generalization approach. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2774–2783
Patrini G, Rozza A, Krishna Menon A, 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, pp 1944–1952
Reed S, Lee H, Anguelov D, Szegedy C, Erhan D, Rabinovich A (2014) Training deep neural networks on noisy labels with bootstrapping. arXiv preprint arXiv:1412.6596
Ren S, He K, Girshick R, Sun J (2016) Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149
Ren M, Zeng W, Yang B, Urtasun R (2018) Learning to reweight examples for robust deep learning. arXiv preprint arXiv:1803.09050
Rolnick D, Veit A, Belongie S, Shavit N (2017) Deep learning is robust to massive label noise. arXiv preprint arXiv:1705.10694
Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC (2015) Imagenet large scale visual recognition challenge. Int J Comput Vision 115(3):211–252
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv: 1409.1556
Sukhbaatar S, Bruna J, Paluri M, Bourdev L, Fergus R (2014) Training convolutional networks with noisy labels. arXiv preprint arXiv:1406.2080
Sun L, Zhao C, Yan Z, Liu P, Duckett T, Stolkin R (2018) A novel weakly-supervised approach for RGB-D-based nuclear waste object detection. IEEE Sens J 19(9):3487–3500
Tang Z, Yu H, Lu C, Liu P, Jin X (2019) Single-trial classification of different movements on one arm based on ERD/ERS and corticomuscular coherence. IEEE Access 7:128185–128197
Vahdat A (2017) Toward robustness against label noise in training deep discriminative neural networks. In: Advances in Neural Information Processing Systems, pp 5596–5605
Van Horn G, Branson S, Farrell R, Haber S, Barry J, Ipeirotis P, Perona P, Belongie S (2015) Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 595–604
Van Rooyen B, Menon A, Williamson RC (2015) Learning with symmetric label noise: The importance of being unhinged. Adv Neural Inf Process Syst 28:10–18
Veit A, Alldrin N, Chechik G, Krasin I, Gupta A, Belongie S (2017) Learning from noisy large-scale datasets with minimal supervision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 839–847
Wang F, Jiang M, Qian C, Yang S, Li C, Zhang H, Wang X, Tang X (2017) Residual attention network for image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3156–3164
Wang Y, Liu W, Ma X, Bailey J, Zha H, Song L, Xia ST (2018) Iterative learning with open-set noisy labels. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 8688–8696
Xiao T, Xia T, Yang Y, Huang C, Wang X (2015) Learning from massive noisy labeled data for image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2691–2699
Yu X, Han B, Yao J, Niu G, Tsang IW, Sugiyama M (2019) How does disagreement help generalization against label corruption? arXiv preprint arXiv:1901.04215
Yuan B, Chen J, Zhang W, Tai HS, McMains S (2018) Iterative cross learning on noisy labels. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, Piscataway, pp 757–765
Zhang Z, Sabuncu M (2018) Generalized cross entropy loss for training deep neural networks with noisy labels. Adv Neural Inf Proces Syst 31:8778–8788
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Ahmed, A., Yousif, H. & He, Z. Ensemble diversified learning for image classification with noisy labels. Multimed Tools Appl 80, 20759–20772 (2021). https://doi.org/10.1007/s11042-021-10760-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-10760-z