Enregistré dans:
Détails bibliographiques
Auteurs principaux: Gerard, Sebastian, Borne-Pons, Paul, Sullivan, Josephine
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2401.17271
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913216060194816
author Gerard, Sebastian
Borne-Pons, Paul
Sullivan, Josephine
author_facet Gerard, Sebastian
Borne-Pons, Paul
Sullivan, Josephine
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2401_17271
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A simple, strong baseline for building damage detection on the xBD dataset
Gerard, Sebastian
Borne-Pons, Paul
Sullivan, Josephine
Computer Vision and Pattern Recognition
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
title A simple, strong baseline for building damage detection on the xBD dataset
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.17271