SPIN: Hierarchical Segmentation with Subpart Granularity in Natural Images
Abstract
Hierarchical segmentation entails creating segmentations at varying levels of granularity. We introduce the first hierarchical semantic segmentation dataset with subpart annotations for natural images, which we call SPIN (SubPartImageNet). We also introduce two novel evaluation metrics to evaluate how well algorithms capture spatial and semantic relationships across hierarchical levels. We benchmark modern models across three different tasks and analyze their strengths and weaknesses across objects, parts, and subparts. To facilitate community-wide progress, we publicly release our dataset at https://joshmyersdean.github. io/spin/index.html.
Cite
Text
Myers-Dean et al. "SPIN: Hierarchical Segmentation with Subpart Granularity in Natural Images." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-72691-0_16Markdown
[Myers-Dean et al. "SPIN: Hierarchical Segmentation with Subpart Granularity in Natural Images." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/myersdean2024eccv-spin/) doi:10.1007/978-3-031-72691-0_16BibTeX
@inproceedings{myersdean2024eccv-spin,
title = {{SPIN: Hierarchical Segmentation with Subpart Granularity in Natural Images}},
author = {Myers-Dean, Josh David and Reynolds, Jarek T and Price, Brian and Fan, Yifei and Gurari, Danna},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2024},
doi = {10.1007/978-3-031-72691-0_16},
url = {https://mlanthology.org/eccv/2024/myersdean2024eccv-spin/}
}