Abstract
ResNet and other CNN networks have a very good performance in the field of image classification, and have developed rapidly in recent years.There are many explanations for the high performance of CNN, which are generally divided into two types: one is shape hypothesis, the other is texture hypothesis. It is found that the dependence of CNNs on texture or shape tends to come from datasets rather than model itself. In this paper, based on CIFAR10 dataset, the texture of the image is partially modified or completely removed, and the stylized image dataset with more shape information is generated. We carried out the experiments of different scale and various stylized-coefficient to study differences comprehensively and multilayered between the influence of stylized-cifar10 dataset with shape information and that of original one with both information and texture information.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Brendel, W., Bethge, M.: Approximating CNNs with bag-of-local-features models works surprisingly well on ImageNet. arXiv preprint arXiv:1904.00760 (2019)
Eckstein, M.P., Koehler, K., Welbourne, L.E., Akbas, E.: Humans, but not deep neural networks, often miss giant targets in scenes. Curr. Biol. 27(18), 2827–2832 (2017)
Emin Orhan, A., Lake, B.M.: Improving the robustness of ImageNet classifiers using elements of human visual cognition. arXiv preprint arXiv:1906.08416 (2019)
Funke, C.M., Gatys, L.A., Ecker, A.S., Bethge, M.: Synthesising dynamic textures using convolutional neural networks. CoRR abs/1702.07006 (2017), http://arxiv.org/abs/1702.07006
Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2414–2423 (2016)
Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., Brendel, W.: ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. CoRR abs/1811.12231 (2018), http://arxiv.org/abs/1811.12231
Geirhos, R., Temme, C.R.M., Rauber, J., Schütt, H.H., Bethge, M., Wichmann, F.A.: Generalisation in humans and deep neural networks. CoRR abs/1808.08750 (2018), http://arxiv.org/abs/1808.08750
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs/1512.03385 (2015), http://arxiv.org/abs/1512.03385
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Kubilius, J., Bracci, S., de Beeck, H.P.O.: Deep neural networks as a computational model for human shape sensitivity. PLoS Comput. Biol. 12(4), e1004896 (2016)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. CoRR abs/1411.4038 (2014), http://arxiv.org/abs/1411.4038
Ritter, S., Barrett, D.G., Santoro, A., Botvinick, M.M.: Cognitive psychology for deep neural networks: a shape bias case study. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp. 2940–2949. JMLR. org (2017)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)
Xie, S., Girshick, R.B., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. CoRR abs/1611.05431 (2016), http://arxiv.org/abs/1611.05431
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53
Acknowledgment
This work is supported by the National Natural Science Foundation of China (61872069), the Fundamental Research Funds for the Central Universities (N2017012).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Wu, D., Xu, J., Liu, H. (2020). Analysis of the Influence of Stylized-CIFAR10 Dataset on ResNet. In: Chen, X., Yan, H., Yan, Q., Zhang, X. (eds) Machine Learning for Cyber Security. ML4CS 2020. Lecture Notes in Computer Science(), vol 12487. Springer, Cham. https://doi.org/10.1007/978-3-030-62460-6_37
Download citation
DOI: https://doi.org/10.1007/978-3-030-62460-6_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-62459-0
Online ISBN: 978-3-030-62460-6
eBook Packages: Computer ScienceComputer Science (R0)