Abstract
In image classification tasks, convolutional neural networks (CNNs) have exhibited higher performance than many other methods. However, some recent studies have shown that CNNs are not shift-invariant, that is, even small spatial shifts in the image can drastically change the output distribution. This finding is non-intuitive because CNNs have long been believed to be shift-invariant. Therefore, we need to measure the shift-invariance of CNNs to better understand the performance of CNNs with respect to image classification. Previous research proposed the utilization of consistency as a metric for measuring shift-invariance. The consistency metric measures how often a CNN classifies the same top-1 class, given two different shifts on the same image. Herein, we identify two shortcomings of the consistency-based approach. First, consistency cannot perfectly capture the change in the output distribution of the CNN because it only considers the top-1 class from the distribution; therefore, other relevant information is lost. Second, the consistency metric is biased by the classification accuracy because the consistency value increases when the images are classified correctly; otherwise, it decreases. To overcome these shortcomings, this paper proposes the correctness-aware distribution distance (CADD). In CADD, we use the Jensen-Shannon (JS) divergence to measure the difference among the entire output distributions. Furthermore, the JS divergence on the correct and incorrect subsets that are split by the classification correctness is separately calculated and averaged. The experimental results demonstrate that the CADD is more stable and interpretable than the consistency-based approach.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Azulay, A., Weiss, Y.: Why do deep convolutional networks generalize so poorly to small image transformations? ArXiv abs/1805.12177 (2018)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Engstrom, L., Tran, B., Tsipras, D., Schmidt, L., Madry, A.: Exploring the landscape of spatial robustness. In: International Conference on Machine Learning (ICML) (2019)
Fukushima, K.: Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36(4), 193–202 (1980). https://doi.org/10.1007/BF00344251
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Krizhevsky, A.: Learning multiple layers of features from tiny images. Technical report (2009)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (NeurIPS) (2012)
LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989)
LeCun, Y., Haffner, P., Bottou, L., Bengio, Y.: Object recognition with gradient-based learning. In: Shape, Contour and Grouping in Computer Vision. LNCS, vol. 1681, pp. 319–345. Springer, Heidelberg (1999). https://doi.org/10.1007/3-540-46805-6_19
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems (NeurIPS) (2019)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning and Representations (ICLR) (2015)
Springenberg, J., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net. In: ICLR (Workshop Track) (2015)
Zhang, R.: Making convolutional networks shift-invariant again. In: International Conference on Machine Learning (ICML) (2019)
Zou, X., Xiao, F., Yu, Z., Lee, Y.J.: Delving deeper into anti-aliasing in convnets. In: British Machine Vision Conference (BMVC) (2020)
Acknowledgement
This study was partly supported with MEXT KAKENHI, Grant-in-Aid for Scientific Research on Innovative Areas, 19H04982, Grant-in-Aid for Scientific Research (A) 18H04106.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Higuchi, H., Suzuki, S., Shouno, H. (2021). Measuring Shift-Invariance of Convolutional Neural Network with a Probability-Incorporated Metric. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Communications in Computer and Information Science, vol 1516. Springer, Cham. https://doi.org/10.1007/978-3-030-92307-5_84
Download citation
DOI: https://doi.org/10.1007/978-3-030-92307-5_84
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92306-8
Online ISBN: 978-3-030-92307-5
eBook Packages: Computer ScienceComputer Science (R0)