mlsanityData to 7 Oct 2026

Investigating the influence of noise and distractors on the interpretation of neural networks

arXiv 1611.07270 ↗First posted 22 Nov 2016stat.ML cs.LGcited by 54

Not on the map. Why?

Abstract (arXiv)

Understanding neural networks is becoming increasingly important. Over the last few years different types of visualisation and explanation methods have been proposed. However, none of them explicitly considered the behaviour in the presence of noise and distracting elements. In this work, we will show how noise and distracting dimensions can influence the result of an explanation model. This gives a new theoretical insights to aid selection of the most appropriate explanation model within the deep-Taylor decomposition framework.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 11; 2023: 11; 2024: 15; 2025: 3; 2026: 1.

54 papers.

Sort:

By area:

  1. 2021Improving Deep Learning Interpretability by Saliency Guided Trainingcited by 68
  2. 2024From Understanding to Utilization: A Survey on Explainability for Large Language Modelscited by 47
  3. 2022GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformerscited by 44
  4. 2021Order in the Court: Explainable AI Methods Prone to Disagreementcited by 36
  5. 2023DecompX: Explaining Transformers Decisions by Propagating Token Decompositioncited by 31
  6. 2021Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classificationcited by 29
  7. 2021CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliencycited by 28
  8. 2024Mechanistic?cited by 25
  9. 2022An Empirical Study on Explanations in Out-of-Domain Settingscited by 21
  10. 2021CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understandingcited by 17
  11. 2021Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Saliencecited by 16
  12. 2023CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibrationcited by 16
38 more
  1. 2022On the Impact of Temporal Concept Drift on Model Explanationscited by 14
  2. 2023Incorporating Attribution Importance for Improving Faithfulness Metricscited by 14
  3. 2022A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processingcited by 13
  4. 2024ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Modelscited by 12
  5. 2021Flexible Instance-Specific Rationalization of NLP Modelscited by 10
  6. 2023SMOOT: Saliency Guided Mask Optimized Online Trainingcited by 8
  7. 2024Full Bayesian Significance Testing for Neural Networkscited by 8
  8. 2021Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifierscited by 6
  9. 2022This Patient Looks Like That Patient: Prototypical Networks for Interpretable Diagnosis Prediction from Clinical Textcited by 6
  10. 2024Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Modelscited by 6
  11. 2024Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Modelscited by 6
  12. 2022Identifying and Characterizing Active Citizens who Refute Misinformation in Social Mediacited by 5
  13. 2023Faithfulness Measurable Masked Language Modelscited by 5
  14. 2024LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributionscited by 5
  15. 2022Backdooring Explainable Machine Learningcited by 4
  16. 2023Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Trainingcited by 4
  17. 2024DUE: Dynamic Uncertainty-Aware Explanation Supervision via 3D Imputationcited by 4
  18. 2024Saliency Assisted Quantization for Neural Networkscited by 4
  19. 2024NormXLogit: The Head-on-Top Never Liescited by 4
  20. 2024Quantized and Interpretable Learning Scheme for Deep Neural Networks in Classification Taskcited by 4
  21. 2025B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainabilitycited by 4
  22. 2021Spatio-Temporal Perturbations for Video Attributioncited by 3
  23. 2022TRUST-LAPSE: An Explainable and Actionable Mistrust Scoring Framework for Model Monitoringcited by 3
  24. 2022Quantitative Metrics for Evaluating Explanations of Video DeepFake Detectorscited by 3
  25. 2022A Rigorous Study Of The Deep Taylor Decompositioncited by 3
  26. 2023XAI-CLASS: Explanation-Enhanced Text Classification with Extremely Weak Supervisioncited by 3
  27. 2024Applications of interpretable deep learning in neuroimaging: a comprehensive reviewcited by 3
  28. 2023Guide the Learner: Controlling Product of Experts Debiasing Method Based on Token Attribution Similaritiescited by 2
  29. 2023Rethinking interpretation: Input-agnostic saliency mapping of deep visual classifierscited by 2
  30. 2021On the Impact of Interpretability Methods in Active Image Augmentation Methodcited by 1
  31. 2024Explanation Regularisation through the Lens of Attributionscited by 1
  32. 2021Attribution Mask: Filtering Out Irrelevant Features By Recursively Focusing Attention on Inputs of DNNscited by 0
  33. 2021It's FLAN time! Summing feature-wise latent representations for interpretabilitycited by 0
  34. 2021"How Does It Detect A Malicious App?" Explaining the Predictions of AI-based Android Malware Detectorcited by 0
  35. 2022Accountable and Explainable Methods for Complex Reasoning over Textcited by 0
  36. 2023CiteCaseLAW: Citation Worthiness Detection in Caselaw for Legal Assistive Writingcited by 0
  37. 2023Reconstruct Before Summarize: An Efficient Two-Step Framework for Condensing and Summarizing Meeting Transcriptscited by 0
  38. 2024NeuralSentinel: Safeguarding Neural Network Reliability and Trustworthinesscited by 0

50 most cited of 54 All 54 (JSON)