Abstract
To intuitively and accurately understand the decision mechanism of Convolutional Neural Networks(CNN), CNN visualization, as an essential part of explainable deep learning, has gradually become a hot topic in artificial intelligence. There have been many achievements in CNN visualization research, such as Gradients, Deconvolution, Class Activation Maps(CAM), etc. But there has been no systematic comparative study on CNN visualization algorithms. The choice of visualization algorithm is critical for accurately explaining the decision process of CNNs. Therefore, an experimental evaluation research on representative CNN visualization algorithms is conducted in this paper for ResNet50 and VGG16 on Caltech101, ImageNet, and VOC2007. The visualization performance is assessed in four aspects: causality, anti-disturbance capability, usability, and computational complexity, and suggestions for selecting CNN visualization algorithms are proposed based on the experimental results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ras, G., Xie, N., Van Gerven, M., Doran, D.: Explainable deep learning: a field guide for the uninitiated. J. Artif. Intell. Res. 73, 329–397 (2022)
Fan, F.L., Xiong, J., Li, M., Wang, G.: On interpretability of artificial neural networks: a survey. IEEE Trans. Radiat. Plasma Med. Sci. 5(6), 741–760 (2021)
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)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Yang, F., Du, M., Hu, X.: Evaluating explanation without ground truth in interpretable machine learning. arXiv preprint arXiv:1907.06831 (2019)
Yang, M., Kim, B.: Benchmarking attribution methods with relative feature importance. arXiv preprint arXiv:1907.09701 (2019)
Brunke, L., Agrawal, P., George, N.: Evaluating input perturbation methods for interpreting CNNs and saliency map comparison. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12535, pp. 120–134. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-66415-2_8
Poppi, S., Cornia, M., Baraldi, L., Cucchiara, R.: Revisiting the evaluation of class activation mapping for explainability: a novel metric and experimental analysis. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2299–2304 (2021)
Samuel, S.Z.S., Kamakshi, V., Lodhi, N., Krishnan, N.C.: Evaluation of saliency-based explainability method. arXiv preprint arXiv:2106.12773 (2021)
Li, J., Lin, D., Wang, Y., Xu, G., Ding, C.: Towards a reliable evaluation of local interpretation methods. Appl. Sci. 11(6), 2732 (2021)
Brocki, L., Chung, N.C.: Evaluation of interpretability methods and perturbation artifacts in deep neural networks. arXiv preprint arXiv:2203.02928 (2022)
Wang, Y., Wang, X.: A unified study of machine learning explanation evaluation metrics. arXiv preprint arXiv:2203.14265 (2022)
Kadir, M.A., Mosavi, A., Sonntag, D.: Assessing xai: unveiling evaluation metrics for local explanation, taxonomies, key concepts, and practical applications
Li, X.H., et al.: Quantitative evaluations on saliency methods: an experimental study. arXiv preprint arXiv:2012.15616 (2020)
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Object detectors emerge in deep scene CNNs. arXiv preprint arXiv:1412.6856 (2014)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)
Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: International Conference on Machine Learning, pp. 3319–3328. PMLR (2017)
Zeiler, M.D., Taylor, G.W., Fergus, R.: Adaptive deconvolutional networks for mid and high level feature learning. In: 2011 International Conference on Computer Vision, pp. 2018–2025. IEEE (2011)
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)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)
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)
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)
Ramaswamy, H.G., et al.: Ablation-cam: visual explanations for deep convolutional network via gradient-free localization. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 983–991 (2020)
Zhang, J., Bargal, S.A., Lin, Z., Brandt, J., Shen, X., Sclaroff, S.: Top-down neural attention by excitation backprop. Int. J. Comput. Vision 126(10), 1084–1102 (2018)
Petsiuk, V., Das, A., Saenko, K.: Rise: randomized input sampling for explanation of black-box models. arXiv preprint arXiv:1806.07421 (2018)
Yeh, C.K., Hsieh, C.Y., Suggala, A., Inouye, D.I., Ravikumar, P.K.: On the (in) fidelity and sensitivity of explanations. Adv. Neural Inf. Process. Syst. 32 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, X., Tu, S., Xue, Y., Chai, L. (2023). Visualizing CNN: An Experimental Comparative Study. In: Lu, H., Blumenstein, M., Cho, SB., Liu, CL., Yagi, Y., Kamiya, T. (eds) Pattern Recognition. ACPR 2023. Lecture Notes in Computer Science, vol 14408. Springer, Cham. https://doi.org/10.1007/978-3-031-47665-5_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-47665-5_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47664-8
Online ISBN: 978-3-031-47665-5
eBook Packages: Computer ScienceComputer Science (R0)