mlsanityData to 14 Oct 2026

A Unified Concept-Based System for Local, Global, and Misclassification Explanations

arXiv 2306.03531 ↗First posted 6 Jun 2023cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Explainability of Deep Neural Networks (DNNs) has been garnering increasing attention in recent years. Of the various explainability approaches, concept-based techniques stand out for their ability to utilize human-meaningful concepts instead of focusing solely on individual pixels. However, there is a scarcity of methods that consistently provide both local and global explanations. Moreover, most of the methods have no offer to explain misclassification cases. Considering these challenges, we present a unified concept-based system for unsupervised learning of both local and global concepts. Our primary objective is to uncover the intrinsic concepts underlying each data category by training surrogate explainer networks to estimate the importance of the concepts. Our experimental results substantiated the efficacy of the discovered concepts through diverse quantitative and qualitative assessments, encompassing faithfulness, completeness, and generality. Furthermore, our approach facilitates the explanation of both accurate and erroneous predictions, rendering it a valuable tool for comprehending the characteristics of the target objects and classes.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 54 references that are in the map. First posted on arXiv 6 Jun 2023.

Builds on

32 of 54 references.

References · 32

  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. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  6. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  7. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  8. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  9. 2014Going Deeper with Convolutionscited by 4,241
  10. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  11. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  12. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
20 more
  1. 2017Interpretation of Neural Networks is Fragilecited by 444
  2. 2017Real Time Image Saliency for Black Box Classifierscited by 246
  3. 2019On Completeness-aware Concept-Based Explanations in Deep Neural Networkscited by 239
  4. 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
  5. 2020Evaluating and Aggregating Feature-based Model Explanationscited by 188
  6. 2019What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Usecited by 135
  7. 2020Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectorscited by 120
  8. 2021Do Feature Attribution Methods Correctly Attribute Features?cited by 98
  9. 2020A survey on modern trainable activation functionscited by 89
  10. 2019Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizationscited by 72
  11. 2019Understanding Neural Networks via Feature Visualization: A surveycited by 65
  12. 2022Learning to Estimate Shapley Values with Vision Transformerscited by 45
  13. 2019Global Explanations of Neural Networks: Mapping the Landscape of Predictionscited by 32
  14. 2019Global and Local Interpretability for Cardiac MRI Classificationcited by 29
  15. 2021Best of both worlds: local and global explanations with human-understandable conceptscited by 22
  16. 2022Concept Embedding Analysis: A Reviewcited by 20
  17. 2017Learning Functional Causal Models with Generative Neural Networkscited by 14
  18. 2020Concept-based model explanations for Electronic Health Recordscited by 14
  19. 2021Efficient Decompositional Rule Extraction for Deep Neural Networkscited by 11
  20. 2021Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Toolscited by 9

Built on by

Not cited yet.