Explainable Convolutional Neural Networks: A Taxonomy, Review, and Future Directions

被引:25
|
作者
Ibrahim, Rami [1 ]
Shafiq, M. Omair [1 ]
机构
[1] Carleton Univ, Sch Informat Technol, 1125 Colonel By Dr, Ottawa, ON K1S 5B6, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Explainable AI; convolutional neural networks; Interpretable AI; survey; DEEP; INTERPRETABILITY; DEFENSE;
D O I
10.1145/3563691
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Convolutional neural networks (CNNs) have shown promising results and have outperformed classical machine learning techniques in tasks such as image classification and object recognition. Their human-brain like structure enabled them to learn sophisticated features while passing images through their layers. However, their lack of explainability led to the demand for interpretations to justify their predictions. Research on Explainable AI or XAI has gained momentum to provide knowledge and insights into neural networks. This study summarizes the literature to gain more understanding of explainability in CNNs (i.e., Explainable Convolutional Neural Networks). We classify models that made efforts to improve the CNNs interpretation. We present and discuss taxonomies for XAI models that modify CNN architecture, simplify CNN representations, analyze feature relevance, and visualize interpretations. We review various metrics used to evaluate XAI interpretations. In addition, we discuss the applications and tasks of XAImodels. This focused and extensive survey develops a perspective on this area by addressing suggestions for overcoming XAI interpretation challenges, like models' generalization, unifying evaluation criteria, building robust models, and providing interpretations with semantic descriptions. Our taxonomy can be a reference to motivate future research in interpreting neural networks.
引用
收藏
页数:37
相关论文
共 50 条
  • [21] Explainable and secure artificial intelligence: taxonomy, cases of study, learned lessons, challenges and future directions
    Eldrandaly, Khalid A.
    Abdel-Basset, Mohamed
    Ibrahim, Mahmoud
    Abdel-Aziz, Nabil M.
    ENTERPRISE INFORMATION SYSTEMS, 2023, 17 (09)
  • [22] A Review on Deep Convolutional Neural Networks
    Aloysius, Neena
    Geetha, M.
    2017 INTERNATIONAL CONFERENCE ON COMMUNICATION AND SIGNAL PROCESSING (ICCSP), 2017, : 588 - 592
  • [23] Big Data Resource Management & Networks: Taxonomy, Survey, and Future Directions
    Awaysheh, Feras M.
    Alazab, Mamoun
    Garg, Sahil
    Niyato, Dusit
    Verikoukis, Christos
    IEEE COMMUNICATIONS SURVEYS AND TUTORIALS, 2021, 23 (04): : 2098 - 2130
  • [24] Explainable Feature Embedding using Convolutional Neural Networks for Pathological Image Analysis
    Uehara, Kazuki
    Murakawa, Masahiro
    Nosato, Hirokazu
    Sakanashi, Hidenori
    2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 4560 - 4565
  • [25] Diabetic retinopathy detection and diagnosis by means of robust and explainable convolutional neural networks
    Mercaldo, Francesco
    Di Giammarco, Marcello
    Apicella, Arianna
    Di Iadarola, Giacomo
    Cesarelli, Mario
    Martinelli, Fabio
    Santone, Antonella
    NEURAL COMPUTING & APPLICATIONS, 2023, 35 (23): : 17429 - 17441
  • [26] Diabetic retinopathy detection and diagnosis by means of robust and explainable convolutional neural networks
    Francesco Mercaldo
    Marcello Di Giammarco
    Arianna Apicella
    Giacomo Di Iadarola
    Mario Cesarelli
    Fabio Martinelli
    Antonella Santone
    Neural Computing and Applications, 2023, 35 : 17429 - 17441
  • [27] Hardware-Aware Evolutionary Explainable Filter Pruning for Convolutional Neural Networks
    Christian Heidorn
    Muhammad Sabih
    Nicolai Meyerhöfer
    Christian Schinabeck
    Jürgen Teich
    Frank Hannig
    International Journal of Parallel Programming, 2024, 52 : 40 - 58
  • [28] Automated Truck Taxonomy Classification Using Deep Convolutional Neural Networks
    Almutairi, Abdullah
    He, Pan
    Rangarajan, Anand
    Ranka, Sanjay
    INTERNATIONAL JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS RESEARCH, 2022, 20 (02) : 483 - 494
  • [29] Identifying Critical Infrastructure in Imagery Data Using Explainable Convolutional Neural Networks
    Elliott, Shiloh N.
    Shields, Ashley J. B.
    Klaehn, Elizabeth M.
    Tien, Iris
    REMOTE SENSING, 2022, 14 (21)
  • [30] XDecompo: Explainable Decomposition Approach in Convolutional Neural Networks for Tumour Image Classification
    Abbas, Asmaa
    Gaber, Mohamed Medhat
    Abdelsamea, Mohammed M.
    SENSORS, 2022, 22 (24)