# Interactive Visualization and Representation Analysis Applied to Glacier Segmentation

arXiv: https://arxiv.org/abs/2112.08184 · HTML: https://mlsanity.com/paper/2112.08184/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 28 references that are in the map.
- First posted on arXiv 11 Dec 2021.

## Builds on (most cited first, 9 of 9)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Understanding Deep Image Representations by Inverting Them](https://mlsanity.com/paper/1412.0035/) (2014)
- [Understanding Neural Networks Through Deep Visualization](https://mlsanity.com/paper/1506.06579/) (2015)
- [Glacier Calving Front Segmentation Using Attention U-Net](https://mlsanity.com/paper/2101.03247/) (2021)
- [Mining self-similarity: Label super-resolution with epitomic representations](https://mlsanity.com/paper/2004.11498/) (2020)
- [Machine Learning for Glacier Monitoring in the Hindu Kush Himalaya](https://mlsanity.com/paper/2012.05013/) (2020)

## Built on by (most cited first, 1 of 1)

- [Boundary Aware U-Net for Glacier Segmentation](https://mlsanity.com/paper/2301.11454/) (2023)

## Abstract (arXiv)

Interpretability has attracted increasing attention in earth observation problems. We apply interactive visualization and representation analysis to guide interpretation of glacier segmentation models. We visualize the activations from a U-Net to understand and evaluate the model performance. We build an online interface using the Shiny R package to provide comprehensive error analysis of the predictions. Users can interact with the panels and discover model failure modes. Further, we discuss how visualization can provide sanity checks during data preprocessing and model training.