Skip to yearly menu bar Skip to main content


Poster

SPIN: Hierarchical Segmentation with Subpart Granularity in Natural Images

josh myers-dean · Jarek T Reynolds · Brian Price · Yifei Fan · Danna Gurari

# 60
Strong blind review: This paper was not made available on public preprint services during the review process Strong Double Blind
[ ] [ Paper PDF ]
[ Supplemental] 
Tue 1 Oct 1:30 a.m. PDT — 3:30 a.m. PDT

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.

Chat is not available.