Diffusion Models for Open-Vocabulary Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Karazija, Laurynas, Laina, Iro, Vedaldi, Andrea, Rupprecht, Christian
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910623838765056
author Karazija, Laurynas
Laina, Iro
Vedaldi, Andrea
Rupprecht, Christian
author_facet Karazija, Laurynas
Laina, Iro
Vedaldi, Andrea
Rupprecht, Christian
contents Open-vocabulary segmentation is the task of segmenting anything that can be named in an image. Recently, large-scale vision-language modelling has led to significant advances in open-vocabulary segmentation, but at the cost of gargantuan and increasing training and annotation efforts. Hence, we ask if it is possible to use existing foundation models to synthesise on-demand efficient segmentation algorithms for specific class sets, making them applicable in an open-vocabulary setting without the need to collect further data, annotations or perform training. To that end, we present OVDiff, a novel method that leverages generative text-to-image diffusion models for unsupervised open-vocabulary segmentation. OVDiff synthesises support image sets for arbitrary textual categories, creating for each a set of prototypes representative of both the category and its surrounding context (background). It relies solely on pre-trained components and outputs the synthesised segmenter directly, without training. Our approach shows strong performance on a range of benchmarks, obtaining a lead of more than 5% over prior work on PASCAL VOC.
format Preprint
id arxiv_https___arxiv_org_abs_2306_09316
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Diffusion Models for Open-Vocabulary Segmentation
Karazija, Laurynas
Laina, Iro
Vedaldi, Andrea
Rupprecht, Christian
Computer Vision and Pattern Recognition
Open-vocabulary segmentation is the task of segmenting anything that can be named in an image. Recently, large-scale vision-language modelling has led to significant advances in open-vocabulary segmentation, but at the cost of gargantuan and increasing training and annotation efforts. Hence, we ask if it is possible to use existing foundation models to synthesise on-demand efficient segmentation algorithms for specific class sets, making them applicable in an open-vocabulary setting without the need to collect further data, annotations or perform training. To that end, we present OVDiff, a novel method that leverages generative text-to-image diffusion models for unsupervised open-vocabulary segmentation. OVDiff synthesises support image sets for arbitrary textual categories, creating for each a set of prototypes representative of both the category and its surrounding context (background). It relies solely on pre-trained components and outputs the synthesised segmenter directly, without training. Our approach shows strong performance on a range of benchmarks, obtaining a lead of more than 5% over prior work on PASCAL VOC.
title Diffusion Models for Open-Vocabulary Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2306.09316