Data to 7 Oct 2026

Interpretable Convolutional Neural Networks

arXiv 1710.00935 ↗First posted 2 Oct 2017cs.CVcited by 161

Not on the map. Why?

Abstract (arXiv)

This paper proposes a method to modify traditional convolutional neural networks (CNNs) into interpretable CNNs, in order to clarify knowledge representations in high conv-layers of CNNs. In an interpretable CNN, each filter in a high conv-layer represents a certain object part. We do not need any annotations of object parts or textures to supervise the learning process. Instead, the interpretable CNN automatically assigns each filter in a high conv-layer with an object part during the learning process. Our method can be applied to different types of CNNs with different structures. The clear knowledge representation in an interpretable CNN can help people understand the logics inside a CNN, i.e., based on which patterns the CNN makes the decision. Experiments showed that filters in an interpretable CNN were more semantically meaningful than those in traditional CNNs.

Key facts. Cited by 161 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 50; 2022: 43; 2023: 31; 2024: 21; 2025: 10; 2026: 6.

161 papers.

Sort:

By area:

2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
2021Trustworthy AI: From Principles to Practicescited by 206
2021Thinking Like Transformerscited by 182
2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 126
2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
2023Concept-based Explainable Artificial Intelligence: A Surveycited by 97
2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
2022Diffusion Models for Counterfactual Explanationscited by 79
2021Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needscited by 64
2022ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognitioncited by 63
2021Synthetic Benchmarks for Scientific Research in Explainable Machine Learningcited by 59

38 more

2024Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Surveycited by 52
2021Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localizationcited by 46
2024Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Directioncited by 46
2021This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagationcited by 43
2021STEEX: Steering Counterfactual Explanations with Semanticscited by 40
2021HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networkscited by 38
2022TopicFM: Robust and Interpretable Topic-Assisted Feature Matchingcited by 32
2021Towards Interpretable Deep Metric Learning with Structural Matchingcited by 30
2022OCTET: Object-aware Counterfactual Explanationscited by 28
2023Text-to-Image Models for Counterfactual Explanations: a Black-Box Approachcited by 28
2021Danish Fungi 2020 -- Not Just Another Image Recognition Datasetcited by 27
2022Causal Reasoning Meets Visual Representation Learning: A Prospective Studycited by 24
2021Carrying out CNN Channel Pruning in a White Boxcited by 22
2022Gait Recognition in the Wild with Multi-hop Temporal Switchcited by 22
2021Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsitycited by 20
2021CX-ToM: Counterfactual Explanations with Theory-of-Mind for Enhancing Human Trust in Image Recognition Modelscited by 20
2022Concept Embedding Analysis: A Reviewcited by 20
2022Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection---Extended Versioncited by 19
2021A Game-Theoretic Taxonomy of Visual Concepts in DNNscited by 16
2021Interpretable Compositional Convolutional Neural Networkscited by 15
2021A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networkscited by 14
2023Illuminati: Towards Explaining Graph Neural Networks for Cybersecurity Analysiscited by 14
2022Interventional Multi-Instance Learning with Deconfounded Instance-Level Predictioncited by 13
2022Sparsely-gated Mixture-of-Expert Layers for CNN Interpretabilitycited by 13
2023Explainability in AI Policies: A Critical Review of Communications, Reports, Regulations, and Standards in the EU, US, and UKcited by 13
2021Towards Interpretable Deep Networks for Monocular Depth Estimationcited by 12
2022Attributable Visual Similarity Learningcited by 12
2023Interpretability of Machine Learning: Recent Advances and Future Prospectscited by 12
2025MOL: Joint Estimation of Micro-Expression, Optical Flow, and Landmark via Transformer-Graph-Style Convolutioncited by 12
2021Comprehensible Convolutional Neural Networks via Guided Concept Learningcited by 11
2021An Overview of Human Activity Recognition Using Wearable Sensors: Healthcare and Artificial Intelligencecited by 11
2022Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attentioncited by 11
2023Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainabilitycited by 11
2021When and How to Fool Explainable Models (and Humans) with Adversarial Examplescited by 10
2023Interpretable and Robust AI in EEG Systems: A Surveycited by 10
2023TopicFM+: Boosting Accuracy and Efficiency of Topic-Assisted Feature Matchingcited by 10
2022ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learningcited by 9
2023Q-SENN: Quantized Self-Explaining Neural Networkscited by 9

50 most cited of 161 All 161 (JSON)