mlsanityData to 7 Oct 2026

Concept Bottleneck Model with Additional Unsupervised Concepts

arXiv 2202.01459 ↗First posted 3 Feb 2022cs.CV cs.AI cs.LGcited by 79

Not on the map. Why?

Abstract (arXiv)

With the increasing demands for accountability, interpretability is becoming an essential capability for real-world AI applications. However, most methods utilize post-hoc approaches rather than training the interpretable model. In this article, we propose a novel interpretable model based on the concept bottleneck model (CBM). CBM uses concept labels to train an intermediate layer as the additional visible layer. However, because the number of concept labels restricts the dimension of this layer, it is difficult to obtain high accuracy with a small number of labels. To address this issue, we integrate supervised concepts with unsupervised ones trained with self-explaining neural networks (SENNs). By seamlessly training these two types of concepts while reducing the amount of computation, we can obtain both supervised and unsupervised concepts simultaneously, even for large-sized images. We refer to the proposed model as the concept bottleneck model with additional unsupervised concepts (CBM-AUC). We experimentally confirmed that the proposed model outperformed CBM and SENN. We also visualized the saliency map of each concept and confirmed that it was consistent with the semantic meanings.

Key facts. Cited by 79 papers in the map (data through 7 Oct 2026). Builds on 32 of its 46 references that are in the map. First posted on arXiv 3 Feb 2022.

Builds on

32 of 46 references.

References · 32

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  7. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  8. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  9. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  10. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  11. 2018Sanity Checks for Saliency Mapscited by 1,149
  12. 2020Concept Bottleneck Modelscited by 1,022
20 more
  1. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  2. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
  3. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  4. 2019On Mutual Information Maximization for Representation Learningcited by 315
  5. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  6. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  7. 2019Mish: A Self Regularized Non-Monotonic Activation Functioncited by 141
  8. 2019Explaining Classifiers with Causal Concept Effect (CaCE)cited by 135
  9. 2021Do Concept Bottleneck Models Learn as Intended?cited by 114
  10. 2020Explainable Object-induced Action Decision for Autonomous Vehiclescited by 88
  11. 2015Part-Stacked CNN for Fine-Grained Visual Categorizationcited by 61
  12. 2017Thinking Fast and Slow: Optimization Decomposition Across Timescalescited by 60
  13. 2019Enhancing Adversarial Defense by k-Winners-Take-Allcited by 51
  14. 2019Interpretability Beyond Classification Output: Semantic Bottleneck Networkscited by 49
  15. 2021Interpretable Models for Granger Causality Using Self-explaining Neural Networkscited by 44
  16. 2018Deep Object-Centric Policies for Autonomous Drivingcited by 41
  17. 2020Debiasing Concept-based Explanations with Causal Analysiscited by 32
  18. 2021Weakly Supervised Multi-task Learning for Concept-based Explainabilitycited by 7
  19. 2020Concept Learners for Few-Shot Learningcited by 3
  20. 2020Visual Concept Reasoning Networkscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 15; 2024: 26; 2025: 23; 2026: 11.

79 papers.

Sort:

By area:

  1. 2022Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classificationcited by 310
  2. 2023Concept-based Explainable Artificial Intelligence: A Surveycited by 97
  3. 2024Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discoverycited by 91
  4. 2023A Closer Look at the Intervention Procedure of Concept Bottleneck Modelscited by 63
  5. 2023Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcutscited by 63
  6. 2024BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcutscited by 36
  7. 2023Auxiliary Losses for Learning Generalizable Concept-based Modelscited by 35
  8. 2023Learning to Intervene on Concept Bottleneckscited by 29
  9. 2024Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?cited by 28
  10. 2022Static and Dynamic Concepts for Self-supervised Video Representation Learningcited by 23
  11. 2024Interpretable Concept Bottlenecks to Align Reinforcement Learning Agentscited by 23
  12. 2022Understanding and Enhancing Robustness of Concept-based Modelscited by 22
38 more
  1. 2023Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learningcited by 22
  2. 2024Editable Concept Bottleneck Modelscited by 22
  3. 2024Semi-supervised Concept Bottleneck Modelscited by 21
  4. 2024A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcutscited by 19
  5. 2024Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?cited by 17
  6. 2024Concept Bottleneck Language Models For protein designcited by 15
  7. 2025If Concept Bottlenecks are the Question, are Foundation Models the Answer?cited by 15
  8. 2024Neural Concept Bindercited by 14
  9. 2025Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lenscited by 13
  10. 2025Leakage and Interpretability in Concept-Based Modelscited by 13
  11. 2023Interpretable and intervenable ultrasonography-based machine learning models for pediatric appendicitiscited by 11
  12. 2023Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainabilitycited by 11
  13. 2025Object Centric Concept Bottleneckscited by 10
  14. 2022C-SENN: Contrastive Self-Explaining Neural Networkcited by 9
  15. 2023Driving through the Concept Gridlock: Unraveling Explainability Bottlenecks in Automated Drivingcited by 9
  16. 2023Concept Distillation: Leveraging Human-Centered Explanations for Model Improvementcited by 9
  17. 2023Q-SENN: Quantized Self-Explaining Neural Networkscited by 9
  18. 2024Intrinsic User-Centric Interpretability through Global Mixture of Expertscited by 9
  19. 2024A survey on Concept-based Approaches For Model Improvementcited by 8
  20. 2023Take 5: Interpretable Image Classification with a Handful of Featurescited by 7
  21. 2024Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Modelscited by 6
  22. 2024Towards Multi-dimensional Explanation Alignment for Medical Classificationcited by 6
  23. 2025Neural Probabilistic Circuits: Enabling Compositional and Interpretable Predictions through Logical Reasoningcited by 6
  24. 2025SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutionscited by 6
  25. 2023Interpretable Graph Neural Networks for Tabular Datacited by 5
  26. 2023Benchmarking and Enhancing Disentanglement in Concept-Residual Modelscited by 5
  27. 2025An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotationscited by 5
  28. 2025Partially Shared Concept Bottleneck Modelscited by 5
  29. 2025LogicCBMs: Logic-Enhanced Concept-Based Learningcited by 5
  30. 2024Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learningcited by 4
  31. 2025A Comprehensive Survey on the Risks and Limitations of Concept-based Modelscited by 4
  32. 2023Bayesian Generalization Error in Linear Neural Networks with Concept Bottleneck Structure and Multitask Formulationcited by 3
  33. 2024Incorporating Expert Rules into Neural Networks in the Framework of Concept-Based Learningcited by 3
  34. 2024Guarding the Gate: ConceptGuard Battles Concept-Level Backdoors in Concept Bottleneck Modelscited by 3
  35. 2025Prediction via Shapley Value Regressioncited by 3
  36. 2025Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Modelscited by 3
  37. 2025Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AIcited by 3
  38. 2024Knowledge graphs for empirical concept retrievalcited by 2

50 most cited of 79 All 79 (JSON)