# From Explanations to Segmentation: Using Explainable AI for Image Segmentation

arXiv: https://arxiv.org/abs/2202.00315 · HTML: https://mlsanity.com/paper/2202.00315/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 1 Feb 2022.

## Builds on (most cited first, 8 of 8)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2001.05566/) (2020)
- [Towards Best Practice in Explaining Neural Network Decisions with LRP](https://mlsanity.com/paper/1910.09840/) (2019)
- [Automatic Analysis of Sewer Pipes Based on Unrolled Monocular Fisheye Images](https://mlsanity.com/paper/1912.05222/) (2019)

## Built on by (most cited first, 5 of 5)

- [Explainable AI (XAI) in Image Segmentation in Medicine, Industry, and Beyond: A Survey](https://mlsanity.com/paper/2405.01636/) (2024)
- [From Classification to Segmentation with Explainable AI: A Study on Crack Detection and Growth Monitoring](https://mlsanity.com/paper/2309.11267/) (2023)
- [WeedNet: A Foundation Model-Based Global-to-Local AI Approach for Real-Time Weed Species Identification and Classification](https://mlsanity.com/paper/2505.18930/) (2025)
- [A Comprehensive Study on Medical Image Segmentation using Deep Neural Networks](https://mlsanity.com/paper/2506.04121/) (2025)
- [No Masks Needed: Explainable AI for Deriving Segmentation from Classification](https://mlsanity.com/paper/2508.04534/) (2025)

## Abstract (arXiv)

The new era of image segmentation leveraging the power of Deep Neural Nets (DNNs) comes with a price tag: to train a neural network for pixel-wise segmentation, a large amount of training samples has to be manually labeled on pixel-precision. In this work, we address this by following an indirect solution. We build upon the advances of the Explainable AI (XAI) community and extract a pixel-wise binary segmentation from the output of the Layer-wise Relevance Propagation (LRP) explaining the decision of a classification network. We show that we achieve similar results compared to an established U-Net segmentation architecture, while the generation of the training data is significantly simplified. The proposed method can be trained in a weakly supervised fashion, as the training samples must be only labeled on image-level, at the same time enabling the output of a segmentation mask. This makes it especially applicable to a wider range of real applications where tedious pixel-level labelling is often not possible.