Abstract
Recently, Convolution Neural Networks (CNN) have achieved excellent performance in some areas of computer vision, including face recognition, character recognition, and autonomous driving. However, there are still many CNN-based models that cannot be deployed in real-world scenarios due to poor robustness. In this paper, focusing on the classification task, we attempt to evaluate and optimize the robustness of CNN-based models from a new perspective: the convolution kernel. Inspired by the discovery that the root cause of the model decision error lies in the wrong response of the convolution kernel, we propose a convolution kernel robustness evaluation metric based on the distribution of convolution kernel responses. Then, we devise the Convolution Kernel Robustness Calibrator, termed as CKR-Calibrator, to optimize key but not robust convolution kernels. Extensive experiments demonstrate that CKR-Calibrator improves the accuracy of existing CNN classifiers by 1%–4% in clean datasets and 1%–5% in corrupt datasets, and improves the accuracy by about 2% over SOTA methods. The evaluation and calibration source code is open-sourced at https://github.com/cym-heu/CKR-Calibrator.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.R., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10(7), e0130140 (2015)
Chattopadhay, A., Sarkar, A., Howlader, P., Balasubramanian, V.N.: Grad-cam++: generalized gradient-based visual explanations for deep convolutional networks. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 839–847. IEEE (2018)
DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. arXiv (2017)
Ding, G.W., Sharma, Y., Lui, K.Y.C., Huang, R.: Mma training: direct input space margin maximization through adversarial training. arXiv (2018)
Feng, Z., Hu, J., Wu, S., Yu, X., Song, J., Song, M.: Model doctor: a simple gradient aggregation strategy for diagnosing and treating CNN classifiers. In: AAAI, vol. 36, pp. 616–624 (2022)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261 (2019)
Hendrycks, D., Mu, N., Cubuk, E.D., Zoph, B., Gilmer, J., Lakshminarayanan, B.: Augmix: a simple data processing method to improve robustness and uncertainty. arXiv (2019)
Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv (2017)
Hu, J., et al.: CNN LEGO: disassembling and assembling convolutional neural network. arXiv (2022)
Huang, G., Liu, Z., Laurens, V.D.M., Weinberger, K.Q.: Densely connected convolutional networks. IEEE Computer Society (2016)
Huang, Y., Chen, Y.: Autonomous driving with deep learning: a survey of state-of-art technologies. arXiv (2020)
Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: Squeezenet: alexnet-level accuracy with 50\(\times \) fewer parameters and< 0.5 mb model size. arXiv preprint arXiv:1602.07360 (2016)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)
Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: NeurIPS, vol. 25, no. 2 (2012)
Lapuschkin, S., Wäldchen, S., Binder, A., Montavon, G., Samek, W., Müller, K.R.: Unmasking clever hans predictors and assessing what machines really learn. Nat. Commun. 10(1), 1096 (2019)
Le, Y., Yang, X.: Tiny imagenet visual recognition challenge. CS 231N 7(7), 3 (2015)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Lengerich, B.J., Konam, S., Xing, E.P., Rosenthal, S., Veloso, M.: Towards visual explanations for convolutional neural networks via input resampling. arXiv (2017)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv (2017)
Miotto, R., Wang, F., Wang, S., Jiang, X., Dudley, J.T.: Deep learning for healthcare: review, opportunities and challenges. Brief. Bioinform. 19(6), 1236–1246 (2018)
Mu, N., Gilmer, J.: Mnist-c: a robustness benchmark for computer vision (2019)
Omeiza, D., Speakman, S., Cintas, C., Weldermariam, K.: Smooth grad-cam++: an enhanced inference level visualization technique for deep convolutional neural network models. arXiv (2019)
Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815–823 (2015)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv (2013)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv (2014)
Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
Szegedy, C., et al.: Intriguing properties of neural networks. arXiv (2013)
Wang, H., et al.: Score-cam: score-weighted visual explanations for convolutional neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 24–25 (2020)
Wei, W., Zhou, J., Wu, Y.: Beyond empirical risk minimization: local structure preserving regularization for improving adversarial robustness. arXiv (2023)
Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. IEEE (2016)
Yang, Y., et al.: Boundary thickness and robustness in learning models. NeurIPS 33, 6223–6234 (2020)
Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: Cutmix: regularization strategy to train strong classifiers with localizable features. In: ICCV, pp. 6023–6032 (2019)
Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv (2016)
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
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. arXiv (2017)
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2929 (2016)
Zintgraf, L.M., Cohen, T.S., Adel, T., Welling, M.: Visualizing deep neural network decisions: prediction difference analysis. arXiv (2017)
Acknowledgements
This work is funded by Public Welfare Technology Applied Research Projects of Zhejiang Province, China (LGG21F020004), Basic Public Welfare Research Project of Zhejiang Province (LGF21F020020), Ningbo Natural Science Foundation (2022J182), and the Fundamental Research Funds for the Central Universities (2021FZZX001-23, 226-2023-00048).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Bei, Y., Geng, J., Liu, E., Gao, K., Huang, W., Feng, Z. (2024). CKR-Calibrator: Convolution Kernel Robustness Evaluation and Calibration. In: Luo, B., Cheng, L., Wu, ZG., Li, H., Li, C. (eds) Neural Information Processing. ICONIP 2023. Lecture Notes in Computer Science, vol 14451. Springer, Singapore. https://doi.org/10.1007/978-981-99-8073-4_11
Download citation
DOI: https://doi.org/10.1007/978-981-99-8073-4_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8072-7
Online ISBN: 978-981-99-8073-4
eBook Packages: Computer ScienceComputer Science (R0)