Boosting Unsupervised Segmentation Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sari, Alp Eren, Locatello, Francesco, Favaro, Paolo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929608121647104
author Sari, Alp Eren
Locatello, Francesco
Favaro, Paolo
author_facet Sari, Alp Eren
Locatello, Francesco
Favaro, Paolo
contents We present two practical improvement techniques for unsupervised segmentation learning. These techniques address limitations in the resolution and accuracy of predicted segmentation maps of recent state-of-the-art methods. Firstly, we leverage image post-processing techniques such as guided filtering to refine the output masks, improving accuracy while avoiding substantial computational costs. Secondly, we introduce a multi-scale consistency criterion, based on a teacher-student training scheme. This criterion matches segmentation masks predicted from regions of the input image extracted at different resolutions to each other. Experimental results on several benchmarks used in unsupervised segmentation learning demonstrate the effectiveness of our proposed techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2404_03392
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Boosting Unsupervised Segmentation Learning
Sari, Alp Eren
Locatello, Francesco
Favaro, Paolo
Computer Vision and Pattern Recognition
We present two practical improvement techniques for unsupervised segmentation learning. These techniques address limitations in the resolution and accuracy of predicted segmentation maps of recent state-of-the-art methods. Firstly, we leverage image post-processing techniques such as guided filtering to refine the output masks, improving accuracy while avoiding substantial computational costs. Secondly, we introduce a multi-scale consistency criterion, based on a teacher-student training scheme. This criterion matches segmentation masks predicted from regions of the input image extracted at different resolutions to each other. Experimental results on several benchmarks used in unsupervised segmentation learning demonstrate the effectiveness of our proposed techniques.
title Boosting Unsupervised Segmentation Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.03392