mlsanityData to 14 Oct 2026

Learning Bottleneck Concepts in Image Classification

arXiv 2304.10131 ↗First posted 20 Apr 2023cs.CVcited by 49

Not on the map. Why?

Abstract (arXiv)

Interpreting and explaining the behavior of deep neural networks is critical for many tasks. Explainable AI provides a way to address this challenge, mostly by providing per-pixel relevance to the decision. Yet, interpreting such explanations may require expert knowledge. Some recent attempts toward interpretability adopt a concept-based framework, giving a higher-level relationship between some concepts and model decisions. This paper proposes Bottleneck Concept Learner (BotCL), which represents an image solely by the presence/absence of concepts learned through training over the target task without explicit supervision over the concepts. It uses self-supervision and tailored regularizers so that learned concepts can be human-understandable. Using some image classification tasks as our testbed, we demonstrate BotCL's potential to rebuild neural networks for better interpretability. Code is available at https://github.com/wbw520/BotCL and a simple demo is available at https://botcl.liangzhili.com/.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Builds on 37 of its 51 references that are in the map. First posted on arXiv 20 Apr 2023.

Builds on

37 of 51 references.

References · 37

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  7. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  8. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  9. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  10. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  11. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  12. 2020Concept Bottleneck Modelscited by 1,032
25 more
  1. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 939
  2. 2020Object-Centric Learning with Slot Attentioncited by 876
  3. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
  4. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  5. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 708
  6. 2020Transformer Interpretability Beyond Attention Visualizationcited by 627
  7. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 582
  8. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  9. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 259
  10. 2019On Completeness-aware Concept-Based Explanations in Deep Neural Networkscited by 239
  11. 2014Object Detectors Emerge in Deep Scene CNNscited by 179
  12. 2021Explainable artificial intelligence (XAI) in deep learning-based medical image analysiscited by 147
  13. 2021TransFG: A Transformer Architecture for Fine-grained Recognitioncited by 132
  14. 2020Restricting the Flow: Information Bottlenecks for Attributioncited by 110
  15. 2019The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanationscited by 97
  16. 2020Interpretable and Accurate Fine-grained Recognition via Region Groupingcited by 75
  17. 2017Learning Semantic Concepts and Order for Image and Sentence Matchingcited by 62
  18. 2019Interpretability Beyond Classification Output: Semantic Bottleneck Networkscited by 49
  19. 2022Quantifying Societal Bias Amplification in Image Captioningcited by 37
  20. 2021A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Conceptscited by 33
  21. 2020SCOUTER: Slot Attention-based Classifier for Explainable Image Recognitioncited by 29
  22. 2021Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representationscited by 24
  23. 2022ECLAD: Extracting Concepts with Local Aggregated Descriptorscited by 15
  24. 2018Semantic bottleneck for computer vision taskscited by 10
  25. 2021Learning Interpretable Concept Groups in CNNscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 23; 2025: 14; 2026: 7.

49 papers.

Sort:

By area:

  1. 2024Incremental Residual Concept Bottleneck Modelscited by 43
  2. 2025Language Guided Concept Bottleneck Models for Interpretable Continual Learningcited by 28
  3. 2024RWKV-CLIP: A Robust Vision-Language Representation Learnercited by 23
  4. 2024Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlookscited by 18
  5. 2024DCBM: Data-Efficient Visual Concept Bottleneck Modelscited by 16
  6. 2024Neural Concept Bindercited by 14
  7. 2025Show and Tell: Visually Explainable Deep Neural Nets via Spatially-Aware Concept Bottleneck Modelscited by 12
  8. 2025Interpretable Image Classification via Non-parametric Part Prototype Learningcited by 11
  9. 2024MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypescited by 10
  10. 2024Evaluating Readability and Faithfulness of Concept-based Explanationscited by 10
  11. 2024Adaptive Concept Bottleneck for Foundation Models Under Distribution Shiftscited by 9
  12. 2025Graph Concept Bottleneck Modelscited by 9
37 more
  1. 2024Generating Counterfactual Trajectories with Latent Diffusion Models for Concept Discoverycited by 8
  2. 2024Urban Safety Perception Assessments via Integrating Multimodal Large Language Models with Street View Imagescited by 8
  3. 2023Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspacecited by 7
  4. 2023MMGPL: Multimodal Medical Data Analysis with Graph Prompt Learningcited by 7
  5. 2024Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Modelscited by 6
  6. 2024Visual Data Diagnosis and Debiasing with Concept Graphscited by 6
  7. 2023Learning Interpretable Queries for Explainable Image Classification with Information Pursuitcited by 5
  8. 2023Coping with Change: Learning Invariant and Minimum Sufficient Representations for Fine-Grained Visual Categorizationcited by 4
  9. 2024Understanding Multimodal Deep Neural Networks: A Concept Selection Viewcited by 4
  10. 2024Improving Concept Alignment in Vision-Language Concept Bottleneck Modelscited by 4
  11. 2025A Comprehensive Survey on the Risks and Limitations of Concept-based Modelscited by 4
  12. 2025Interpretable Decision-Making for End-to-End Autonomous Drivingcited by 4
  13. 2024Incorporating Expert Rules into Neural Networks in the Framework of Concept-Based Learningcited by 3
  14. 2024A Self-explaining Neural Architecture for Generalizable Concept Learningcited by 3
  15. 2023SurroCBM: Concept Bottleneck Surrogate Models for Generative Post-hoc Explanationcited by 2
  16. 2024Explainable Image Recognition via Enhanced Slot-attention Based Classifiercited by 2
  17. 2024TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Modelscited by 2
  18. 2025A Survey on Interpretability in Visual Recognitioncited by 2
  19. 2026Differentiable Rule Induction from Raw Sequence Inputscited by 2
  20. 2024ECATS: Explainable-by-design concept-based anomaly detection for time seriescited by 1
  21. 2024ConceptHash: Interpretable Fine-Grained Hashing via Concept Discoverycited by 1
  22. 2024FI-CBL: A Probabilistic Method for Concept-Based Learning with Expert Rulescited by 1
  23. 2024DEPICT: Diffusion-Enabled Permutation Importance for Image Classification Taskscited by 1
  24. 2025ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformerscited by 1
  25. 2025Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discoverycited by 1
  26. 2025Towards Better Generalization and Interpretability in Unsupervised Concept-Based Modelscited by 1
  27. 2025Multi-Modal Feature Fusion for Spatial Morphology Analysis of Traditional Villages via Hierarchical Graph Neural Networkscited by 1
  28. 2024Bi-ICE: An Inner Interpretable Framework for Image Classification via Bi-directional Interactions between Concept and Input Embeddingscited by 0
  29. 2025When concept-based XAI is imprecise: Do people distinguish between generalisations and misrepresentations?cited by 0
  30. 2025Are Inherently Interpretable Models More Robust? A Study In Music Emotion Recognitioncited by 0
  31. 2025The Impact of Concept Explanations and Interventions on Human-Machine Collaborationcited by 0
  32. 2026Federated Concept-Based Models: Interpretable models with distributed supervisioncited by 0
  33. 2026Toward Faithful Segmentation Attribution via Benchmarking and Dual-Evidence Fusioncited by 0
  34. 2026What-Where Transformer: A Slot-Centric Visual Backbone for Concurrent Representation and Localizationcited by 0
  35. 2026Naming the Concepts Classifiers Rely On: Language-Anchored Decomposition for Faithful Explanationcited by 0
  36. 2026Identifying Confusion Trends in Concept-based XAI for Multi-Label Classificationcited by 0
  37. 2026DF-CBM: Region-Aware Concept Bottleneck Models for Deepfake Detectioncited by 0