# Explanations for Occluded Images

arXiv: https://arxiv.org/abs/2103.03622 · HTML: https://mlsanity.com/paper/2103.03622/

## Key facts

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

## Builds on (most cited first, 17 of 17)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Understanding Deep Networks via Extremal Perturbations and Smooth Masks](https://mlsanity.com/paper/1910.08485/) (2019)
- [Learning to Explain: An Information-Theoretic Perspective on Model Interpretation](https://mlsanity.com/paper/1802.07814/) (2018)
- [Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks](https://mlsanity.com/paper/1904.00605/) (2019)
- [A Modification of the Halpern-Pearl Definition of Causality](https://mlsanity.com/paper/1505.00162/) (2015)
- [Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion](https://mlsanity.com/paper/2003.04490/) (2020)
- [Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusion](https://mlsanity.com/paper/1905.11826/) (2019)
- [Robustness of Object Recognition under Extreme Occlusion in Humans and Computational Models](https://mlsanity.com/paper/1905.04598/) (2019)
- [Unsupervised learning of object semantic parts from internal states of CNNs by population encoding](https://mlsanity.com/paper/1511.06855/) (2015)
- [Defining Explanation in Probabilistic Systems](https://mlsanity.com/paper/1302.1526/) (2013)

## Built on by (most cited first, 14 of 14)

- [The role of causality in explainable artificial intelligence](https://mlsanity.com/paper/2309.09901/) (2023)
- [Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasons](https://mlsanity.com/paper/2502.03391/) (2025)
- [Explaining Image Classifiers](https://mlsanity.com/paper/2401.13752/) (2024)
- [Occlusion Sensitivity Analysis with Augmentation Subspace Perturbation in Deep Feature Space](https://mlsanity.com/paper/2311.15022/) (2023)
- [Self-Explaining Neural Networks for Business Process Monitoring](https://mlsanity.com/paper/2503.18067/) (2025)
- [Approaching an unknown communication system by latent space exploration and causal inference](https://mlsanity.com/paper/2303.10931/) (2023)
- [Multiple Different Black Box Explanations for Image Classifiers](https://mlsanity.com/paper/2309.14309/) (2023)
- [A Stochastic Approach to Classification Error Estimates in Convolutional Neural Networks](https://mlsanity.com/paper/2401.06156/) (2023)
- [Illuminating Salient Contributions in Neuron Activation with Attribution Equilibrium](https://mlsanity.com/paper/2205.11109/) (2022)
- [Statistical relational learning and neuro-symbolic AI: what does first-order logic offer?](https://mlsanity.com/paper/2306.13660/) (2023)
- [I Guess That's Why They Call it the Blues: Causal Analysis for Audio Classifiers](https://mlsanity.com/paper/2601.16675/) (2026)
- [Ablation Path Saliency](https://mlsanity.com/paper/2209.12459/) (2022)
- [It's a Feature, Not a Bug: Measuring Creative Fluidity in Image Generators](https://mlsanity.com/paper/2406.18570/) (2024)
- [Robot Pouring: Identifying Causes of Spillage and Selecting Alternative Action Parameters Using Probabilistic Actual Causation](https://mlsanity.com/paper/2502.09395/) (2025)

## 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.