Saved in:
Bibliographic Details
Main Authors: Dille, Sebastian, Blondal, Ari, Paris, Sylvain, Aksoy, Yağız
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.13687
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909321279832064
author Dille, Sebastian
Blondal, Ari
Paris, Sylvain
Aksoy, Yağız
author_facet Dille, Sebastian
Blondal, Ari
Paris, Sylvain
Aksoy, Yağız
contents Class-agnostic image segmentation is a crucial component in automating image editing workflows, especially in contexts where object selection traditionally involves interactive tools. Existing methods in the literature often adhere to top-down formulations, following the paradigm of class-based approaches, where object detection precedes per-object segmentation. In this work, we present a novel bottom-up formulation for addressing the class-agnostic segmentation problem. We supervise our network directly on the projective sphere of its feature space, employing losses inspired by metric learning literature as well as losses defined in a novel segmentation-space representation. The segmentation results are obtained through a straightforward mean-shift clustering of the estimated features. Our bottom-up formulation exhibits exceptional generalization capability, even when trained on datasets designed for class-based segmentation. We further showcase the effectiveness of our generic approach by addressing the challenging task of cell and nucleus segmentation. We believe that our bottom-up formulation will offer valuable insights into diverse segmentation challenges in the literature.
format Preprint
id arxiv_https___arxiv_org_abs_2409_13687
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Bottom-Up Approach to Class-Agnostic Image Segmentation
Dille, Sebastian
Blondal, Ari
Paris, Sylvain
Aksoy, Yağız
Computer Vision and Pattern Recognition
Class-agnostic image segmentation is a crucial component in automating image editing workflows, especially in contexts where object selection traditionally involves interactive tools. Existing methods in the literature often adhere to top-down formulations, following the paradigm of class-based approaches, where object detection precedes per-object segmentation. In this work, we present a novel bottom-up formulation for addressing the class-agnostic segmentation problem. We supervise our network directly on the projective sphere of its feature space, employing losses inspired by metric learning literature as well as losses defined in a novel segmentation-space representation. The segmentation results are obtained through a straightforward mean-shift clustering of the estimated features. Our bottom-up formulation exhibits exceptional generalization capability, even when trained on datasets designed for class-based segmentation. We further showcase the effectiveness of our generic approach by addressing the challenging task of cell and nucleus segmentation. We believe that our bottom-up formulation will offer valuable insights into diverse segmentation challenges in the literature.
title A Bottom-Up Approach to Class-Agnostic Image Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.13687