Interactive Visualization and Representation Analysis Applied to Glacier Segmentation
Not on the map. Why?
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.
Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 9 of its 28 references that are in the map. First posted on arXiv 11 Dec 2021.
Builds on
9 of 28 references.
References · 9
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,656
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,360
- 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,522
- 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 551
- 2014Understanding Deep Image Representations by Inverting Themcited by 400
- 2015Understanding Neural Networks Through Deep Visualizationcited by 333
- 2021Glacier Calving Front Segmentation Using Attention U-Netcited by 10
- 2020Mining self-similarity: Label super-resolution with epitomic representationscited by 6
- 2020Machine Learning for Glacier Monitoring in the Hindu Kush Himalayacited by 4
Built on by
Citing papers per year: 2023: 1.
1 paper.
- 2023Boundary Aware U-Net for Glacier Segmentationcited by 1
- 2023Boundary Aware U-Net for Glacier Segmentation26 Jan 2023