# U-Noise: Learnable Noise Masks for Interpretable Image Segmentation

arXiv: https://arxiv.org/abs/2101.05791 · HTML: https://mlsanity.com/paper/2101.05791/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 16 references that are in the map.
- First posted on arXiv 14 Jan 2021.

## Builds on (most cited first, 14 of 14)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [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)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1505.05424/) (2015)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [Women also Snowboard: Overcoming Bias in Captioning Models](https://mlsanity.com/paper/1803.09797/) (2018)
- [Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mapping](https://mlsanity.com/paper/2002.11434/) (2020)
- [Grid Saliency for Context Explanations of Semantic Segmentation](https://mlsanity.com/paper/1907.13054/) (2019)
- [Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation](https://mlsanity.com/paper/1702.05174/) (2017)
- [Not All Features Are Equal: Discovering Essential Features for Preserving Prediction Privacy](https://mlsanity.com/paper/2003.12154/) (2020)

## Built on by (most cited first, 9 of 9)

- [Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations](https://mlsanity.com/paper/2211.11426/) (2022)
- [Explainable AI (XAI) in Image Segmentation in Medicine, Industry, and Beyond: A Survey](https://mlsanity.com/paper/2405.01636/) (2024)
- [When Differential Privacy Meets Interpretability: A Case Study](https://mlsanity.com/paper/2106.13203/) (2021)
- [Voxel-level Importance Maps for Interpretable Brain Age Estimation](https://mlsanity.com/paper/2108.05388/) (2021)
- [Towards Explainable AI for Channel Estimation in Wireless Communications](https://mlsanity.com/paper/2307.00952/) (2023)
- [Trainable Noise Model as an XAI evaluation method: application on Sobol for remote sensing image segmentation](https://mlsanity.com/paper/2310.01828/) (2023)
- [MiSuRe is all you need to explain your image segmentation](https://mlsanity.com/paper/2406.12173/) (2024)
- [Applications of interpretable deep learning in neuroimaging: a comprehensive review](https://mlsanity.com/paper/2406.17792/) (2024)
- [Efficient KernelSHAP Explanations for Patch-based 3D Medical Image Segmentation](https://mlsanity.com/paper/2604.11775/) (2026)

## Abstract (arXiv)

Deep Neural Networks (DNNs) are widely used for decision making in a myriad of critical applications, ranging from medical to societal and even judicial. Given the importance of these decisions, it is crucial for us to be able to interpret these models. We introduce a new method for interpreting image segmentation models by learning regions of images in which noise can be applied without hindering downstream model performance. We apply this method to segmentation of the pancreas in CT scans, and qualitatively compare the quality of the method to existing explainability techniques, such as Grad-CAM and occlusion sensitivity. Additionally we show that, unlike other methods, our interpretability model can be quantitatively evaluated based on the downstream performance over obscured images.