mlsanityData to 14 Oct 2026

Missingness Bias in Model Debugging

arXiv 2204.08945 ↗First posted 19 Apr 2022cs.CV cs.AI cs.LGcited by 38

Not on the map. Why?

Abstract (arXiv)

Missingness, or the absence of features from an input, is a concept fundamental to many model debugging tools. However, in computer vision, pixels cannot simply be removed from an image. One thus tends to resort to heuristics such as blacking out pixels, which may in turn introduce bias into the debugging process. We study such biases and, in particular, show how transformer-based architectures can enable a more natural implementation of missingness, which side-steps these issues and improves the reliability of model debugging in practice. Our code is available at https://github.com/madrylab/missingness

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Builds on 52 of its 61 references that are in the map. First posted on arXiv 19 Apr 2022.

Builds on

52 of 61 references.

References · 52

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  8. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  9. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  10. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  11. 2013Intriguing properties of neural networkscited by 5,155
  12. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
38 more
  1. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  2. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  3. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  4. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  5. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  6. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
  7. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  8. 2018Sanity Checks for Saliency Mapscited by 1,156
  9. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  10. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 708
  11. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 612
  12. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 476
  13. 2021Intriguing Properties of Vision Transformerscited by 446
  14. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 419
  15. 2020Asymmetric Loss For Multi-Label Classificationcited by 381
  16. 2020Noise or Signal: The Role of Image Backgrounds in Object Recognitioncited by 343
  17. 2017The (Un)reliability of saliency methodscited by 333
  18. 2019Counterfactual Visual Explanationscited by 313
  19. 2019On the (In)fidelity and Sensitivity for Explanationscited by 310
  20. 2018Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negativescited by 262
  21. 2017Real Time Image Saliency for Black Box Classifierscited by 246
  22. 2019On Completeness-aware Concept-Based Explanations in Deep Neural Networkscited by 239
  23. 2020Explaining by Removing: A Unified Framework for Model Explanationcited by 218
  24. 2015Visualizing and Understanding Neural Models in NLPcited by 200
  25. 2021On the Robustness of Vision Transformers to Adversarial Examplescited by 167
  26. 2017Visualizing Deep Neural Network Decisions: Prediction Difference Analysiscited by 166
  27. 2018Explaining Image Classifiers by Counterfactual Generationcited by 144
  28. 2018Benchmarking Neural Network Robustness to Common Corruptions and Surface Variationscited by 99
  29. 2021Do Feature Attribution Methods Correctly Attribute Features?cited by 98
  30. 2018Grounding Visual Explanationscited by 93
  31. 2019Benchmarking Attribution Methods with Relative Feature Importancecited by 89
  32. 2021Leveraging Sparse Linear Layers for Debuggable Deep Networkscited by 82
  33. 2018How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanationcited by 72
  34. 2020Understanding Failures of Deep Networks via Robust Feature Extractioncited by 56
  35. 2021Certified Patch Robustness via Smoothed Vision Transformerscited by 45
  36. 2016Object Recognition with and without Objectscited by 39
  37. 2019Do Explanations Reflect Decisions? A Machine-centric Strategy to Quantify the Performance of Explainability Algorithmscited by 32
  38. 20213DB: A Framework for Debugging Computer Vision Modelscited by 31

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 8; 2024: 9; 2025: 9; 2026: 6.

38 papers.

Sort:

By area:

  1. 2023Discovering and Mitigating Visual Biases through Keyword Explanationcited by 58
  2. 2023Diagnosing and Rectifying Vision Models using Languagecited by 58
  3. 2022Learning to Estimate Shapley Values with Vision Transformerscited by 45
  4. 2022A Data-Based Perspective on Transfer Learningcited by 32
  5. 2024Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarkscited by 28
  6. 2023Estimating Conditional Mutual Information for Dynamic Feature Selectioncited by 21
  7. 2023GLIME: General, Stable and Local LIME Explanationcited by 21
  8. 2024Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attributioncited by 21
  9. 2024Locality Alignment Improves Vision-Language Modelscited by 13
  10. 2025Probabilistic Stability Guarantees for Feature Attributionscited by 9
  11. 2022Towards Improved Input Masking for Convolutional Neural Networkscited by 8
  12. 2023Take 5: Interpretable Image Classification with a Handful of Featurescited by 7
26 more
  1. 2022SHAP-XRT: The Shapley Value Meets Conditional Independence Testingcited by 6
  2. 2023Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groupscited by 6
  3. 2024Diffexplainer: Towards Cross-modal Global Explanations with Diffusion Modelscited by 5
  4. 2024On the Evaluation Consistency of Attribution-based Explanationscited by 5
  5. 2024What could go wrong? Discovering and describing failure modes in computer visioncited by 5
  6. 2024T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformerscited by 4
  7. 2024Layerwise Change of Knowledge in Neural Networkscited by 4
  8. 2025Towards Human-Understandable Multi-Dimensional Concept Discoverycited by 4
  9. 2025Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifierscited by 4
  10. 2022Data-Centric Debugging: mitigating model failures via targeted data collectioncited by 3
  11. 2025Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibrationcited by 3
  12. 2025Concept Regions Matter: Benchmarking CLIP with a New Cluster-Importance Approachcited by 3
  13. 2022Weakly Supervised Learning Significantly Reduces the Number of Labels Required for Intracranial Hemorrhage Detection on Head CTcited by 1
  14. 2025Rethinking Explanation Evaluation under the Retraining Schemecited by 1
  15. 2025Back to the Baseline: Examining Baseline Effects on Explainability Metricscited by 1
  16. 2026Missingness Bias Calibration in Feature Attribution Explanationscited by 1
  17. 2026Scaling Inherently Interpretable Language Modelscited by 1
  18. 2023Impact of architecture on robustness and interpretability of multispectral deep neural networkscited by 0
  19. 2023Explanation-based Training with Differentiable Insertion/Deletion Metric-aware Regularizerscited by 0
  20. 2024Explaining Black-box Model Predictions via Two-level Nested Feature Attributions with Consistency Propertycited by 0
  21. 2025Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanationscited by 0
  22. 2025Token-Based Detection of Spurious Correlations in Vision Transformerscited by 0
  23. 2026XtrAIn: Training-Guided Occlusion for Feature Attributioncited by 0
  24. 2026Signal or Noise? Auditing Rotation-Induced Saliency Drift in Medical and Aerial Imagingcited by 0
  25. 2026Mask-Induced Displacement in Audio XAI via Logit Trajectory Decompositioncited by 0
  26. 2026ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attributioncited by 0