Abstract
Deep convolutional neural networks (DCNNs) have achieved significant performance on image classification task. How to use more powerful loss function to train robust DCNN for image classification has become a recent trend in the community. In this paper, we present an elegant yet effective loss function: Constrictive Annular Loss (CA-Loss), to boost the classification performance of the DCNNs. CA-Loss can adaptively constrict the features to a suitable scale leading to more representative features, even for the imbalanced dataset. CA-Loss can be easily combined with softmax loss to jointly supervise the DCNNs. Furthermore, CA-Loss does not require additional supervisory information, and it can be easily optimized by the classical optimization algorithm (e.g. Stochastic gradient descent). We conduct extensive experiments on two large scale classification benchmarks and three artificially imbalanced datasets. CA-Loss achieves the state-of-the-art accuracy on these datasets, which strongly demonstrates the effectiveness of our proposed loss function.
Similar content being viewed by others
References
Facebook (2017) Pytorch. https://pytorch.org/
Goodfellow IJ, Warde-Farley D, Mirza M, Courville A, Bengio Y (2013) Maxout networks. arXiv:13024389
He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, pp 1026–1034
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, pp 770–778
He K, Gkioxari G, Dollár P, Girshick R (2017) Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 2980–2988
Huang G, Liu Z, Maaten LVD, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2261–2269
Krizhevsky A (2009) Learning multiple layers of features from tiny images. Technical Report
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
Lecun Y, Cortes C (1998) The mnist database of handwritten digits. Technical Report
Lin M, Chen Q, Yan S (2013) Network in network. arXiv:13124400
Lin TY, Goyal P, Girshick R, He K, Dollar P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision, pp 2999–3007
Liu W, Wen Y, Yu Z, Yang M (2016) Large-margin softmax loss for convolutional neural networks. In: Proceedings of 33rd international conference on machine learning, pp 507–516
Liu W, Wen Y, Yu Z, Li M, Raj B, Song L (2017) Sphereface: deep hypersphere embedding for face recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6738–6746
Liu Y, Li H, Wang X (2017) Learning deep features via congenerous cosine loss for person recognition. arXiv:170206890
Liu Y, Li H, Wang X (2017) Rethinking feature discrimination and polymerization for large-scale recognition. arXiv:171000870
Patryk C, Ilya L, Frank H (2017) A downsampled variant of imagenet as an alternative to the cifar datasets. arXiv:170708819
Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252
Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 815–823
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:14091556
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958
Sun Y, Chen Y, Wang X, Tang X (2014) Deep learning face representation by joint identification-verification. In: Advances in neural information processing systems, pp 1988–1996
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9
Wan L, Zeiler M, Zhang S, Le Cun Y, Fergus R (2013) Regularization of neural networks using dropconnect. In: Proceedings of 30th international conference on machine learning, pp 1058– 1066
Wang F, Xiang X, Cheng J, Yuille AL (2017) Normface: L2 hypersphere embedding for face verification. In: Proceedings of 25th ACM international conference on multimedia, pp 1041– 1049
Wang F, Cheng J, Liu W, Liu H (2018) Additive margin softmax for face verification. IEEE Signal Process Lett 25(7):926–930
Wang L, Yin B, Guo A, Ma H, Cao J (2018) Skip-connection convolutional neural network for still image crowd counting. Appl Intell 48(6):3360–3371
Wang X, Zhang S, Lei Z, Liu S, Guo X, Li SZ (2018) Ensemble soft-margin softmax loss for image classification. In: Proceedings of the international joint conferences on artificial intelligence, pp 992–998
Wen Y, Zhang K, Li Z, Qiao Y (2016) A discriminative feature learning approach for deep face recognition. In: Proceedings of the European conference on computer vision, pp 499–515
Xie S, Girshick R, Dollar P, Tu Z, He K (2017) Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5987–5995
Zagoruyko S, Komodakis N (2015) Learning to compare image patches via convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4353–4361
Zeiler MD, Fergus R (2013) Stochastic pooling for regularization of deep convolutional neural networks. arXiv:13013557
Acknowledgements
This work is supported by the Natural Science Foundation of China (Grant No. 61273364).
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
Liu, JB., Huang, YP., Zou, Q. et al. Learning representative features via constrictive annular loss for image classification. Appl Intell 49, 3082–3092 (2019). https://doi.org/10.1007/s10489-019-01434-3
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-019-01434-3