mlsanityData to 14 Oct 2026

Explain Any Concept: Segment Anything Meets Concept-Based Explanation

arXiv 2305.10289 ↗First posted 17 May 2023cs.CV cs.AIcited by 37

Not on the map. Why?

Abstract (arXiv)

EXplainable AI (XAI) is an essential topic to improve human understanding of deep neural networks (DNNs) given their black-box internals. For computer vision tasks, mainstream pixel-based XAI methods explain DNN decisions by identifying important pixels, and emerging concept-based XAI explore forming explanations with concepts (e.g., a head in an image). However, pixels are generally hard to interpret and sensitive to the imprecision of XAI methods, whereas "concepts" in prior works require human annotation or are limited to pre-defined concept sets. On the other hand, driven by large-scale pre-training, Segment Anything Model (SAM) has been demonstrated as a powerful and promotable framework for performing precise and comprehensive instance segmentation, enabling automatic preparation of concept sets from a given image. This paper for the first time explores using SAM to augment concept-based XAI. We offer an effective and flexible concept-based explanation method, namely Explain Any Concept (EAC), which explains DNN decisions with any concept. While SAM is highly effective and offers an "out-of-the-box" instance segmentation, it is costly when being integrated into defacto XAI pipelines. We thus propose a lightweight per-input equivalent (PIE) scheme, enabling efficient explanation with a surrogate model. Our evaluation over two popular datasets (ImageNet and COCO) illustrate the highly encouraging performance of EAC over commonly-used XAI methods.

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). Builds on 36 of its 53 references that are in the map. First posted on arXiv 17 May 2023.

Builds on

36 of 53 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2023Segment Anythingcited by 8,234
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  7. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  8. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  9. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  10. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  11. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  12. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
24 more
  1. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  2. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  3. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  4. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
  5. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 612
  6. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 419
  7. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 349
  8. 2019On Completeness-aware Concept-Based Explanations in Deep Neural Networkscited by 239
  9. 2020Evaluating and Aggregating Feature-based Model Explanationscited by 188
  10. 2022CRAFT: Concept Recursive Activation FacTorization for Explainabilitycited by 178
  11. 2020Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regressioncited by 154
  12. 2019Explaining Classifiers with Causal Concept Effect (CaCE)cited by 135
  13. 2019Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximationcited by 115
  14. 2021What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methodscited by 98
  15. 2015Visualizing Deep Convolutional Neural Networks Using Natural Pre-Imagescited by 93
  16. 2023SAM on Medical Images: A Comprehensive Study on Three Prompt Modescited by 82
  17. 2023Impact Of Explainable AI On Cognitive Load: Insights From An Empirical Studycited by 15
  18. 2021Roadmap of Designing Cognitive Metrics for Explainable Artificial Intelligence (XAI)cited by 13
  19. 2017Beyond saliency: understanding convolutional neural networks from saliency prediction on layer-wise relevance propagationcited by 10
  20. 2021Instance-wise or Class-wise? A Tale of Neighbor Shapley for Concept-based Explanationcited by 9
  21. 2022XInsight: eXplainable Data Analysis Through The Lens of Causalitycited by 9
  22. 2022Learning Visual Explanations for DCNN-Based Image Classifiers Using an Attention Mechanismcited by 7
  23. 2023TAME: Attention Mechanism Based Feature Fusion for Generating Explanation Maps of Convolutional Neural Networkscited by 6
  24. 2022Unveiling Hidden DNN Defects with Decision-Based Metamorphic Testingcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 17; 2025: 9; 2026: 8.

37 papers.

Sort:

By area:

  1. 2023EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anythingcited by 188
  2. 2023Review of Large Vision Models and Visual Prompt Engineeringcited by 77
  3. 2024Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agendacited by 22
  4. 2024Efficient Track Anythingcited by 21
  5. 2024Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlookscited by 18
  6. 2024Eliminating Information Leakage in Hard Concept Bottleneck Models with Supervised, Hierarchical Concept Learningcited by 17
  7. 2024DCBM: Data-Efficient Visual Concept Bottleneck Modelscited by 16
  8. 2024Evaluating Readability and Faithfulness of Concept-based Explanationscited by 10
  9. 2025CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantificationcited by 9
  10. 2025FACE: Faithful Automatic Concept Extractioncited by 9
  11. 2024Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Modelscited by 8
  12. 2024Interpreting Low-level Vision Models with Causal Effect Mapscited by 8
25 more
  1. 2025Which LIME should I trust? Concepts, Challenges, and Solutionscited by 8
  2. 2024Superpixel Tokenization for Vision Transformers: Preserving Semantic Integrity in Visual Tokenscited by 7
  3. 2024VALE: A Multimodal Visual and Language Explanation Framework for Image Classifiers using eXplainable AI and Language Modelscited by 4
  4. 2025Towards Human-Understandable Multi-Dimensional Concept Discoverycited by 4
  5. 2024Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representationscited by 3
  6. 2025C-SHAP for time series: An approach to high-level temporal explanationscited by 3
  7. 2024LCE: A Framework for Explainability of DNNs for Ultrasound Image Based on Concept Discoverycited by 2
  8. 2024Multi-Depth Concept Extraction for Post-Hoc Vision Encoder Explanationcited by 2
  9. 2025A Survey on Interpretability in Visual Recognitioncited by 2
  10. 2026Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraintscited by 2
  11. 2026ShapBPT: Image Feature Attributions Using Data-Aware Binary Partition Treescited by 2
  12. 2023TVE: Learning Meta-attribution for Transferable Vision Explainercited by 1
  13. 2024Deep spatial context: when attention-based models meet spatial regressioncited by 1
  14. 2024Beyond Attribution: Unified Concept-Level Explanationscited by 1
  15. 2025Aggregating Local Saliency Maps for Semi-Global Explainable Image Classificationcited by 1
  16. 2026PhaseWin: An Efficient Search Algorithm for Faithful Visual Attributioncited by 1
  17. 2024Improving the Explain-Any-Concept by Introducing Nonlinearity to the Trainable Surrogate Modelcited by 0
  18. 2024Spoof Trace Discovery for Deep Learning Based Explainable Face Anti-Spoofingcited by 0
  19. 2025P-TAME: Explain Any Image Classifier with Trained Perturbationscited by 0
  20. 2025ProtoMask: Segmentation-Guided Prototype Learningcited by 0
  21. 2026Explainable AI to Improve Machine Learning Reliability for Industrial Cyber-Physical Systemscited by 0
  22. 2026Focus-LIME: Surgical Interpretation of Long-Context Large Language Models via Proxy-Based Neighborhood Selectioncited by 0
  23. 2026Revealing Interpretable Failure Modes of VLMscited by 0
  24. 2026A Good Initialization is All You Need for Faithful Visual Attributioncited by 0
  25. 2026MorphoSHAP: Rethinking the Unit of Attribution in Explanation for Deep Visual Modelscited by 0