Abstract
With Artificial Intelligence advancement, Deep neural networks (DNN) are extensively used for decision-making in intelligent systems. However, improved performance and accuracy have been achieved through the increasing use of complex models, which makes it challenging for users to understand and trust. This ambiguous nature of these Deep machine learning models of high accuracy and low interpretability is problematic for their adoption in critical domains where it is vital to be able to explain the decisions made by the system. Explainable Artificial Intelligence has become an exciting field for explaining and interpreting machine learning models. Among the different data types used in machine learning, image data is considered hard to train because of the factors such as class, scale, viewpoint, and background variations. This paper aims to provide a rounded view of emerging methods to explain DNN models as a way to boost transparency in image-based deep learning with the analysis of the current and upcoming trends.
Similar content being viewed by others
References
Sze V, Chen YH, Yang TJ, Emer JS (2017) Efficient processing of deep neural networks: a tutorial and survey. Proc IEEE 105:2295–2329
Adadi A, Berrada M (2018) Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6:52160
Preece AD, Harborne D, Braines D, Tomsett R, Chakraborty S (2018) Stakeholders in Explainable AIa. CoRR, vol. bs/1810.00184
Schlegel U, Arnout H, El-Assady M, Oelke D, Keim DA (2019) Towards a rigorous evaluation of xai methods on time series. 2019 IEEE/CVF International conference on computer vision workshop (ICCVW), pp. 4197–4201
Kaminski ME (2019) The right to explanation, explained. Berkeley Tech LJ 34:189–189
Yang, M., Wang, H., Hu, K., Yin, G., & Wei, Z. (2022). IA-Net: An Inception–Attention-Module-Based Network for Classifying Underwater Images From Others. IEEE Journal of Oceanic Engineering, 47(3), 704–717. https://doi.org/10.1109/JOE.2021.3126090
Arrieta AB (2020) Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf Fusion 58:82–115
Guidotti R, Monreale A, Ruggieri S, Turini F, Giannotti F, Pedreschi D (2018) A survey of methods for explaining black box models. ACM Comput Surv 51(5):1–42
Montavon G, Samek W, Müller KR (2018) Methods for interpreting and understanding deep neural networks. Digit Signal Process 73:1–15
Fernandez A, Herrera F, Cordon O, Jesus MJ, Marcelloni F (2019) Evolutionary fuzzy systems for explainable artificial intelligence: why, when, what for, and where to? IEEE Comput Intell Mag 14(1):69–81
Lipton ZC (2018) The mythos of model interpretability: in machine learning, the concept of interpretability is both important and slippery. pp. 31–57
Mohseni S, Zarei N, Ragan ED (2018) A multidisciplinary survey and framework for design and evaluation of explainable AI systems
Zhou, W., Wang, H., & Wan, Z. (2022). Ore Image Classification Based on Improved CNN. Computers & electrical engineering, 99(1). https://doi.org/10.1016/j.compeleceng.2022.107819
Bhatt U (2020) Explainable machine learning in deployment. Proceedings of the 2020 conference on fairness, accountability, and transparency. pp. 648–657
Choo J, Liu S (2018) Visual analytics for explainable deep learning. IEEE Comput Graph Appl 38(4):84–92
Liu, H., Liu, M., Li, D., Zheng, W., Yin, L.,... Wang, R. (2022). Recent Advances in Pulse-Coupled Neural Networks with Applications in Image Processing. Electronics, 11(20). https://doi.org/10.3390/electronics11203264
Das A, Rad P (2020) Opportunities and challenges in explainable artificial intelligence (XAI): a survey. CoRR. vol. abs/2006.11371
Ivanovs M, Kadikis R, Ozols K (2021) Perturbation-based methods for explaining deep neural networks: a survey. Pattern Recognit Lett
Yang L, Kenny EM, Ng TLJ, Yang Y, Smyth B, Dong R (2020) generating plausible counterfactual explanations for deep transformers in financial text classification. CoRR, vol. abs/2010.12512
Zhao, L., & Wang, L. (2022). A new lightweight network based on MobileNetV3. KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS. https://doi.org/10.3837/tiis.2022.01.001
Ploug T, Holm S (2020) The four dimensions of contestable AI diagnosticsA patient-centric approach to explainable AI. Artif Intell Med 107:101–901
Huang, C., Jiang, F., Huang, Q., Wang, X., Han, Z.,... Huang, W. (2022). Dual-Graph Attention Convolution Network for 3-D Point Cloud Classification. IEEE Transactions on Neural Networks and Learning Systems, 1–13. https://doi.org/10.1109/TNNLS.2022.3162301
Jiawei Xu, Sicheng Pan, Poly Z.H. Sun, Seop Hyeong Park, and Kun Guo, “Human-Factors-in-Driving-Loop: Driver Identification and Verification via a Deep Learning Approach using Psychological Behavioral Data,” IEEE Transactions on Intelligent Transportation Systems (IEEE-TITS), 2022. https://doi.org/10.1109/TITS.2022.3225782
Pak M, Kim S, (2017) A review of deep learning in image recognition. 2017 4th international conference on computer applications and information processing technology, pp. 1–3
Dong Y, Su H, Zhu J, Zhang B (2017) Improving interpretability of deep neural networks with semantic information. Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 4306–4314
Zhuang, Y., Chen, S., Jiang, N., & Hu, H. (2022). An Effective WSSENet-Based Similarity Retrieval Method of Large Lung CT Image Databases. KSII Transactions on Internet & Information Systems, 16(7). https://doi.org/10.3837/tiis.2022.07.013
Cortez P, Embrechts MJ (2011) Opening black box data mining models using sensitivity analysis. 2011 IEEE Symposium on computational intelligence and data mining (CIDM), pp. 341–348
Cortex P (2013) Using sensitivity analysis and visualization techniques to open black box data mining models. Inf Sci 225:1–17
Caruana R (2000) Case-based explanation for artificial neural nets. In Artificial neural networks in medicine and biology. pp. 303–308
Keane MT, Kenny EM (2019) The twin-system approach as one generic solution for XAI: an overview of ANN-CBR twins for explaining deep learning. CoRR, vol. abs/1905.08069
Guidotti R, Monreale A, Ruggieri S, Pedreschi D, Turini F, Giannotti F (2018) Local rule-based explanations of black box decision systems,” CoRR, vol. abs/1805.10820
Krishnan S, Wu E (2017) Palm: machine learning explanations for iterative debugging. Proceedings of the 2nd workshop on human-in-the-loop data analytics. pp. 1–6
Ribeiro MT, Singh S, Guestrin C (2016) ‘Why should i trust you?’ Explaining the predictions of any classifier. Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining, vol. 13
Simonyan K, Vedaldi A, Zisserman A (2014) Deep inside convolutional networks: visualising image classification models and saliency maps. CoRR, vol. abs/1312.6034
Shrikumar A, Greenside P, Shcherbina A, Kundaje A, (2016) Not just a black box: learning important features through propagating activation differences. CoRR, vol. abs/1605.01713
Xu, S., He, Q., Tao, S., Chen, H., Chai, Y.,... Zheng, W. (2022). Pig Face Recognition Based on Trapezoid Normalized Pixel Difference Feature and Trimmed Mean Attention Mechanism. IEEE Transactions on Instrumentation and Measurement, 1. https://doi.org/10.1109/TIM.2022.3232093
Springenberg JT, Dosovitskiy A, Brox T, Riedmiller MA (2015) Striving for simplicity: the all convolutional net. CoRR, vol. abs/1412.6806
Bach S, Binder A, Montavon G, Klauschen F, Müller KR, Samek W (2015) On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS One 10(7):140–130
Kindermans P-J, Schütt KT, Alber M, Müller K-R, Erhan D, Kim B, Dähne S (2018) Learning how to explain neural networks: PatternNet and PatternAttribution,” in ICLR
Sundararajan M, Taly A, Yan Q (2017) Axiomatic attribution for deep networks. 34th International conference on machine learning, vol. 7
Shrikumar A, Greenside P, Kundaje A (2017) Learning important features through propagating activation differences. International conference on machine learning. pp. 3145–3153
Ancona M, Ceolini E, Öztireli AC, Gross MH, (2017) A unified view of gradient-based attribution methods for deep neural networks. CoRR, vol. abs/1711.06104
Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A (2016) Learning deep features for discriminative localization. Proceedings of the IEEE computer society conference on computer vision and pattern recognition
Lin M, Chen Q, Yan S (2014) Network in network. CoRR, vol. abs/1312.4400
Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-cam: visual explanations from deep networks via gradientbased localization. Proceedings of the IEEE international conference on computer vision. pp. 618–626
Chattopadhay A, Sarkar A, Howlader P, Balasubramanian VN (2018) Grad-CAM++: generalized gradient-based visual explanations for deep convolutional networks. Proceedings 2018 IEEE winter conference on applications of computer vision
Smilkov D, Thorat N, Kim B, Viégas FB, Wattenberg M (2017) SmoothGrad: removing noise by adding noise. CoRR, vol. abs/1706.03825
Aumann RJ, Shapley LS (2016) Values of non-atomic games. Princeton University Press, Princeton
Mitchell R, Cooper J, Frank E, Holmes G, (2021) Sampling permutations for shapley value estimation
Lundberg SM, Lee SI (2017) A unified approach to interpreting model predictions. Advances in neural information processing systems. pp. 2017–2017
Chen H, Lundberg S, Lee SI (2021) Explaining models by propagating shapley values of local components. Studies in computational intelligence. vol. 914
Ancona M, Oztireli C, Gross M (2019) Explaining deep neural networks with a polynomial time algorithm for shapley value approximation. International conference on machine learning. pp. 272–281
Petsiuk V, Das A, Saenko K (2018) Rise: randomized input sampling for explanation of black-box models
Zintgraf LM, Cohen TS, Adel T, Welling M, (2017) Visualizing deep neural network decisions: prediction difference analysis. CoRR, vol. abs/1702.04595
Burns C, Thomason J, Tansey W (2020) Interpreting black box models via hypothesis testing. Proceedings of the 2020 ACM-IMS on foundations of data science conference. pp. 47–57
Fong RC, Vedaldi A (2017) Interpretable explanations of black boxes by meaningful perturbation. Proceedings of the IEEE international conference on computer vision. pp. 3429–3437
Dabkowski P, Gal Y (2017) Real time image saliency for black box classifiers. In Proceedings of the 31st international conference on neural information processing systems. Red Hook, NY, USA: Curran Associates Inc., pp. 6970–6979
Fong R, Patrick M, Vedaldi A (2019) Understanding deep networks via extremal perturbations and smooth masks. Proceedings of the IEEE/CVF international conference on computer vision. pp. 2950–2958
Yang Q, Zhu X, Fwu JK, Ye Y, You G, Zhu Y (2021) MFPP: morphological fragmental perturbation pyramid for black-box model explanations. 2020 25th International conference on pattern recognition (ICPR). pp. 1376–1383
Kim B (2018) Interpretability beyond feature attribution: quantitative testing with concept activation vectors (tcav). In International conference on machine learning. pp. 2668–2677
Ghorbani A, Wexler J, Zou J, Kim B (2019) Towards Automatic ConceptBased Explanations. Curran Associates Inc., Red Hook, NY, USA
Goyal Y, Shalit U, Kim B (2019) Explaining classifiers with causal concept effect (CaCE). CoRR, vol. abs/1907.07165
Agarwal R, Frosst N, Zhang X, Caruana R, Hinton GE (2020) Neural additive models: interpretable machine learning with neural nets. CoRR, vol. abs/2004.13912
Lapuschkin S, Wäldchen S, Binder A, Montavon G, Samek W, Müller KR (2019) Unmasking clever hans predictors and assessing what machines really learn. Nat Commun 10(1):1–8
Ibrahim M, Louie M, Modarres C, Paisley J (2019) Global explanations of neural networks: Mapping the landscape of predictions. Proceedings of the 2019 AAAI/ACM conference on AI, pp. 279–287
Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. 2009 IEEE conference on computer vision and pattern recognition, pp. 248–255
Krizhevsky A, Hinton G (2009) Learning multiple layers of features from tiny images
Russakovsky O (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252
Deng L (2012) The mnist database of handwritten digit images for machine learning research. IEEE Signal Process Mag 29(6):141–142
Huang, G. B., Mattar, M., Berg, T., & Learned-Miller, E. (2008, October). Labeled faces in the wild: A database forstudying face recognition in unconstrained environments. In Workshop on faces in‘Real-Life’Images: detection, alignment, and recognition.
Everingham M, Gool LV, Williams CKI, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303–338
Lin TY (2014) Microsoft coco: common objects in context. pp. 740–755
Kim B, Kim H, Kim K, Kim S, Kim J, (2019) Learning not to learn: training deep neural networks with biased data. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), June 2019
Yang M, Kim B (2019) BIM: towards quantitative evaluation of interpretability methods with ground truth. ArXiv, vol. abs/1907.09701
Eykholt K (2018) Robust physical-world attacks on deep learning visual classification. Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 1625–1634
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
There is no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Gupta, L.K., Koundal, D. & Mongia, S. Explainable Methods for Image-Based Deep Learning: A Review. Arch Computat Methods Eng 30, 2651–2666 (2023). https://doi.org/10.1007/s11831-023-09881-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11831-023-09881-5