mlsanityData to 7 Oct 2026

Explanations for Occluded Images

arXiv 2103.03622 ↗First posted 5 Mar 2021cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Existing algorithms for explaining the output of image classifiers perform poorly on inputs where the object of interest is partially occluded. We present a novel, black-box algorithm for computing explanations that uses a principled approach based on causal theory. We have implemented the method in the DEEPCOVER tool. We obtain explanations that are much more accurate than those generated by the existing explanation tools on images with occlusions and observe a level of performance comparable to the state of the art when explaining images without occlusions.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 17 of its 38 references that are in the map. First posted on arXiv 5 Mar 2021.

Builds on

17 of 38 references.

References · 17

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  6. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  7. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  8. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  9. 2019Understanding Deep Networks via Extremal Perturbations and Smooth Maskscited by 257
  10. 2018Learning to Explain: An Information-Theoretic Perspective on Model Interpretationcited by 248
  11. 2019Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networkscited by 49
  12. 2015A Modification of the Halpern-Pearl Definition of Causalitycited by 47
5 more
  1. 2020Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusioncited by 47
  2. 2019Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusioncited by 24
  3. 2019Robustness of Object Recognition under Extreme Occlusion in Humans and Computational Modelscited by 18
  4. 2015Unsupervised learning of object semantic parts from internal states of CNNs by population encodingcited by 8
  5. 2013Defining Explanation in Probabilistic Systemscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 6; 2024: 2; 2025: 3; 2026: 1.

14 papers.

Sort:

  1. 2023The role of causality in explainable artificial intelligencecited by 17
  2. 2025Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasonscited by 11
  3. 2024Explaining Image Classifierscited by 7
  4. 2023Occlusion Sensitivity Analysis with Augmentation Subspace Perturbation in Deep Feature Spacecited by 6
  5. 2025Self-Explaining Neural Networks for Business Process Monitoringcited by 5
  6. 2023Approaching an unknown communication system by latent space exploration and causal inferencecited by 4
  7. 2023Multiple Different Black Box Explanations for Image Classifierscited by 4
  8. 2023A Stochastic Approach to Classification Error Estimates in Convolutional Neural Networkscited by 3
  9. 2022Illuminating Salient Contributions in Neuron Activation with Attribution Equilibriumcited by 1
  10. 2023Statistical relational learning and neuro-symbolic AI: what does first-order logic offer?cited by 1
  11. 2026I Guess That's Why They Call it the Blues: Causal Analysis for Audio Classifierscited by 1
  12. 2022Ablation Path Saliencycited by 0
2 more
  1. 2024It's a Feature, Not a Bug: Measuring Creative Fluidity in Image Generatorscited by 0
  2. 2025Robot Pouring: Identifying Causes of Spillage and Selecting Alternative Action Parameters Using Probabilistic Actual Causationcited by 0