Studying Image Diffusion Features for Zero-Shot Video Object Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Delatolas, Thanos, Kalogeiton, Vicky, Papadopoulos, Dim P.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910905653002240
author Delatolas, Thanos
Kalogeiton, Vicky
Papadopoulos, Dim P.
author_facet Delatolas, Thanos
Kalogeiton, Vicky
Papadopoulos, Dim P.
contents This paper investigates the use of large-scale diffusion models for Zero-Shot Video Object Segmentation (ZS-VOS) without fine-tuning on video data or training on any image segmentation data. While diffusion models have demonstrated strong visual representations across various tasks, their direct application to ZS-VOS remains underexplored. Our goal is to find the optimal feature extraction process for ZS-VOS by identifying the most suitable time step and layer from which to extract features. We further analyze the affinity of these features and observe a strong correlation with point correspondences. Through extensive experiments on DAVIS-17 and MOSE, we find that diffusion models trained on ImageNet outperform those trained on larger, more diverse datasets for ZS-VOS. Additionally, we highlight the importance of point correspondences in achieving high segmentation accuracy, and we yield state-of-the-art results in ZS-VOS. Finally, our approach performs on par with models trained on expensive image segmentation datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2504_05468
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Studying Image Diffusion Features for Zero-Shot Video Object Segmentation
Delatolas, Thanos
Kalogeiton, Vicky
Papadopoulos, Dim P.
Computer Vision and Pattern Recognition
This paper investigates the use of large-scale diffusion models for Zero-Shot Video Object Segmentation (ZS-VOS) without fine-tuning on video data or training on any image segmentation data. While diffusion models have demonstrated strong visual representations across various tasks, their direct application to ZS-VOS remains underexplored. Our goal is to find the optimal feature extraction process for ZS-VOS by identifying the most suitable time step and layer from which to extract features. We further analyze the affinity of these features and observe a strong correlation with point correspondences. Through extensive experiments on DAVIS-17 and MOSE, we find that diffusion models trained on ImageNet outperform those trained on larger, more diverse datasets for ZS-VOS. Additionally, we highlight the importance of point correspondences in achieving high segmentation accuracy, and we yield state-of-the-art results in ZS-VOS. Finally, our approach performs on par with models trained on expensive image segmentation datasets.
title Studying Image Diffusion Features for Zero-Shot Video Object Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.05468