# A simple, strong baseline for building damage detection on the xBD dataset

arXiv: https://arxiv.org/abs/2401.17271 · HTML: https://mlsanity.com/paper/2401.17271/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 11 references that are in the map.
- First posted on arXiv 30 Jan 2024.

## Builds on (most cited first, 5 of 5)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Are we done with ImageNet?](https://mlsanity.com/paper/2006.07159/) (2020)
- [xBD: A Dataset for Assessing Building Damage from Satellite Imagery](https://mlsanity.com/paper/1911.09296/) (2019)
- [Why Do Better Loss Functions Lead to Less Transferable Features?](https://mlsanity.com/paper/2010.16402/) (2020)

## Built on by (most cited first, 4 of 4)

- [BRIGHT: A globally distributed multimodal building damage assessment dataset with very-high-resolution for all-weather disaster response](https://mlsanity.com/paper/2501.06019/) (2025)
- [A Change Detection Reality Check](https://mlsanity.com/paper/2402.06994/) (2024)
- [Robust Building Damage Detection in Cross-Disaster Settings Using Domain Adaptation](https://mlsanity.com/paper/2603.14694/) (2026)
- [Leveraging Satellite Image Time Series for Accurate Extreme Event Detection](https://mlsanity.com/paper/2506.11544/) (2025)

## Abstract (arXiv)

We construct a strong baseline method for building damage detection by starting with the highly-engineered winning solution of the xView2 competition, and gradually stripping away components. This way, we obtain a much simpler method, while retaining adequate performance. We expect the simplified solution to be more widely and easily applicable. This expectation is based on the reduced complexity, as well as the fact that we choose hyperparameters based on simple heuristics, that transfer to other datasets. We then re-arrange the xView2 dataset splits such that the test locations are not seen during training, contrary to the competition setup. In this setting, we find that both the complex and the simplified model fail to generalize to unseen locations. Analyzing the dataset indicates that this failure to generalize is not only a model-based problem, but that the difficulty might also be influenced by the unequal class distributions between events. Code, including the baseline model, is available under https://github.com/PaulBorneP/Xview2_Strong_Baseline