mlsanityData to 7 Oct 2026

Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks

arXiv 1904.00605 ↗First posted 1 Apr 2019cs.CVcited by 49

Not on the map. Why?

Abstract (arXiv)

As Deep Neural Networks (DNNs) have demonstrated superhuman performance in a variety of fields, there is an increasing interest in understanding the complex internal mechanisms of DNNs. In this paper, we propose Relative Attributing Propagation (RAP), which decomposes the output predictions of DNNs with a new perspective of separating the relevant (positive) and irrelevant (negative) attributions according to the relative influence between the layers. The relevance of each neuron is identified with respect to its degree of contribution, separated into positive and negative, while preserving the conservation rule. Considering the relevance assigned to neurons in terms of relative priority, RAP allows each neuron to be assigned with a bi-polar importance score concerning the output: from highly relevant to highly irrelevant. Therefore, our method makes it possible to interpret DNNs with much clearer and attentive visualizations of the separated attributions than the conventional explaining methods. To verify that the attributions propagated by RAP correctly account for each meaning, we utilize the evaluation metrics: (i) Outside-inside relevance ratio, (ii) Segmentation mIOU and (iii) Region perturbation. In all experiments and metrics, we present a sizable gap in comparison to the existing literature. Our source code is available in urlhttps://github.com/wjNam/RelativeAttributingPropagation.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 7; 2023: 10; 2024: 7; 2025: 9; 2026: 1.

49 papers.

Sort:

By area:

  1. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 316
  2. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  3. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  4. 2024The Hidden Attention of Mamba Modelscited by 88
  5. 2022Optimizing Relevance Maps of Vision Transformers Improves Robustnesscited by 41
  6. 2021Focus! Rating XAI Methods and Finding Biasescited by 20
  7. 2024On the Faithfulness of Vision Transformer Explanationscited by 19
  8. 2021Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoringcited by 16
  9. 2021Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixingcited by 15
  10. 2022Debiasing Deep Chest X-Ray Classifiers using Intra- and Post-processing Methodscited by 15
  11. 2021Explanations for Occluded Imagescited by 14
  12. 2021Latent Space Explanation by Interventioncited by 13
37 more
  1. 2024Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulationcited by 11
  2. 2024Towards Modeling Uncertainties of Self-explaining Neural Networks via Conformal Predictioncited by 10
  3. 2022From Modern CNNs to Vision Transformers: Assessing the Performance, Robustness, and Classification Strategies of Deep Learning Models in Histopathologycited by 9
  4. 2025Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIPcited by 7
  5. 2023Disentangling Structure and Style: Political Bias Detection in News by Inducing Document Hierarchycited by 6
  6. 2023Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groupscited by 6
  7. 2021MISA: Online Defense of Trojaned Models using Misattributionscited by 4
  8. 2021Explanatory Pluralism in Explainable AIcited by 4
  9. 2023Multiple Different Black Box Explanations for Image Classifierscited by 4
  10. 2021Finding Representative Interpretations on Convolutional Neural Networkscited by 3
  11. 2023Learning to Explain: A Model-Agnostic Framework for Explaining Black Box Modelscited by 3
  12. 2023It Ain't That Bad: Understanding the Mysterious Performance Drop in OOD Generalization for Generative Transformer Modelscited by 2
  13. 2023SPADE: Sparsity-Guided Debugging for Deep Neural Networkscited by 2
  14. 2023How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors?cited by 2
  15. 2023You Only Explain Oncecited by 2
  16. 2025Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partitioncited by 2
  17. 2021NEWRON: A New Generalization of the Artificial Neuron to Enhance the Interpretability of Neural Networkscited by 1
  18. 2021Learning a Weight Map for Weakly-Supervised Localizationcited by 1
  19. 2022Illuminating Salient Contributions in Neuron Activation with Attribution Equilibriumcited by 1
  20. 2022Generalizability Analysis of Graph-based Trajectory Predictor with Vectorized Representationcited by 1
  21. 2023Explaining the Decisions of Deep Policy Networks for Robotic Manipulationscited by 1
  22. 2023Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidancecited by 1
  23. 2024Advancing Attribution-Based Neural Network Explainability through Relative Absolute Magnitude Layer-Wise Relevance Propagation and Multi-Component Evaluationcited by 1
  24. 2025Probing Network Decisions: Capturing Uncertainties and Unveiling Vulnerabilities Without Label Informationcited by 1
  25. 2025PnPXAI: A Universal XAI Framework Providing Automatic Explanations Across Diverse Modalities and Modelscited by 1
  26. 2025Out-of-the-box: Black-box Causal Attacks on Object Detectorscited by 1
  27. 2021Weakly Supervised Recovery of Semantic Attributescited by 0
  28. 2021Explainability Guided Multi-Site COVID-19 CT Classificationcited by 0
  29. 2021Improving Interpretability of Deep Neural Networks in Medical Diagnosis by Investigating the Individual Unitscited by 0
  30. 2022Interpretable Diabetic Retinopathy Diagnosis based on Biomarker Activation Mapcited by 0
  31. 2024TranSentence: Speech-to-speech Translation via Language-agnostic Sentence-level Speech Encoding without Language-parallel Datacited by 0
  32. 2024Model Guidance via Explanations Turns Image Classifiers into Segmentation Modelscited by 0
  33. 2025Evaluation of Black-Box XAI Approaches for Predictors of Values of Boolean Formulaecited by 0
  34. 2025EVO-LRP: Evolutionary Optimization of LRP for Interpretable Model Explanationscited by 0
  35. 2025Semantic Prioritization in Visual Counterfactual Explanations with Weighted Segmentation and Auto-Adaptive Region Selectioncited by 0
  36. 2025Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Designcited by 0
  37. 2026Few-class Fidelity: Evaluating Explanations of Real-conditions CNN classifiers with Optimized Perturbationscited by 0