mlsanityData to 7 Oct 2026

What does LIME really see in images?

arXiv 2102.06307 ↗First posted 11 Feb 2021cs.LG cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

The performance of modern algorithms on certain computer vision tasks such as object recognition is now close to that of humans. This success was achieved at the price of complicated architectures depending on millions of parameters and it has become quite challenging to understand how particular predictions are made. Interpretability methods propose to give us this understanding. In this paper, we study LIME, perhaps one of the most popular. On the theoretical side, we show that when the number of generated examples is large, LIME explanations are concentrated around a limit explanation for which we give an explicit expression. We further this study for elementary shape detectors and linear models. As a consequence of this analysis, we uncover a connection between LIME and integrated gradients, another explanation method. More precisely, the LIME explanations are similar to the sum of integrated gradients over the superpixels used in the preprocessing step of LIME.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 13 of its 24 references that are in the map. First posted on arXiv 11 Feb 2021.

Builds on

13 of 24 references.

References · 13

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  7. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  8. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  9. 2014Deep Learning in Neural Networks: An Overviewcited by 765
  10. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 440
  11. 2020Explaining the Explainer: A First Theoretical Analysis of LIMEcited by 89
  12. 2020An Analysis of LIME for Text Datacited by 25
1 more
  1. 2020Looking Deeper into Tabular LIMEcited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 4; 2023: 5; 2024: 5; 2025: 4; 2026: 1.

21 papers.

Sort:

  1. 2023GLIME: General, Stable and Local LIME Explanationcited by 21
  2. 2022The Manifold Hypothesis for Gradient-Based Explanationscited by 15
  3. 2022Identifying Spurious Correlations and Correcting them with an Explanation-based Learningcited by 10
  4. 2021Ensembles of Random SHAPscited by 8
  5. 2024Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Modelscited by 8
  6. 2021An Imprecise SHAP as a Tool for Explaining the Class Probability Distributions under Limited Training Datacited by 6
  7. 2022A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculturecited by 6
  8. 2024Provably Better Explanations with Optimized Aggregation of Feature Attributionscited by 6
  9. 2024CAM-Based Methods Can See through Wallscited by 4
  10. 2024Study on the Helpfulness of Explainable Artificial Intelligencecited by 4
  11. 2024Using Stratified Sampling to Improve LIME Image Explanationscited by 3
  12. 2025On The Variability of Concept Activation Vectorscited by 3
9 more
  1. 2023On the Robustness of Text Vectorizerscited by 2
  2. 2025Attribution Explanations for Deep Neural Networks: A Theoretical Perspectivecited by 2
  3. 2022How to scale hyperparameters for quickshift image segmentationcited by 1
  4. 2025Feature Attribution from First Principlescited by 1
  5. 2023Stop overkilling simple tasks with black-box models and use transparent models insteadcited by 0
  6. 2023Fairness Explainability using Optimal Transport with Applications in Image Classificationcited by 0
  7. 2023SurvBeNIM: The Beran-Based Neural Importance Model for Explaining the Survival Modelscited by 0
  8. 2025MindfulLIME: A Stable Solution for Explanations of Machine Learning Models with Enhanced Localization Precision -- A Medical Image Case Studycited by 0
  9. 2026Inpainting Insights: Elevating Visual XAI with Photorealistic Perturbationscited by 0