Rethinking Alignment and Uniformity in Unsupervised Semantic Segmentation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Daoan, Li, Chenming, Li, Haoquan, Huang, Wenjian, Huang, Lingyun, Zhang, Jianguo
Format: Preprint
Publié: 2022
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910735251013632
author Zhang, Daoan
Li, Chenming
Li, Haoquan
Huang, Wenjian
Huang, Lingyun
Zhang, Jianguo
author_facet Zhang, Daoan
Li, Chenming
Li, Haoquan
Huang, Wenjian
Huang, Lingyun
Zhang, Jianguo
contents Unsupervised image semantic segmentation(UISS) aims to match low-level visual features with semantic-level representations without outer supervision. In this paper, we address the critical properties from the view of feature alignments and feature uniformity for UISS models. We also make a comparison between UISS and image-wise representation learning. Based on the analysis, we argue that the existing MI-based methods in UISS suffer from representation collapse. By this, we proposed a robust network called Semantic Attention Network(SAN), in which a new module Semantic Attention(SEAT) is proposed to generate pixel-wise and semantic features dynamically. Experimental results on multiple semantic segmentation benchmarks show that our unsupervised segmentation framework specializes in catching semantic representations, which outperforms all the unpretrained and even several pretrained methods.
format Preprint
id arxiv_https___arxiv_org_abs_2211_14513
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Rethinking Alignment and Uniformity in Unsupervised Semantic Segmentation
Zhang, Daoan
Li, Chenming
Li, Haoquan
Huang, Wenjian
Huang, Lingyun
Zhang, Jianguo
Computer Vision and Pattern Recognition
Artificial Intelligence
Unsupervised image semantic segmentation(UISS) aims to match low-level visual features with semantic-level representations without outer supervision. In this paper, we address the critical properties from the view of feature alignments and feature uniformity for UISS models. We also make a comparison between UISS and image-wise representation learning. Based on the analysis, we argue that the existing MI-based methods in UISS suffer from representation collapse. By this, we proposed a robust network called Semantic Attention Network(SAN), in which a new module Semantic Attention(SEAT) is proposed to generate pixel-wise and semantic features dynamically. Experimental results on multiple semantic segmentation benchmarks show that our unsupervised segmentation framework specializes in catching semantic representations, which outperforms all the unpretrained and even several pretrained methods.
title Rethinking Alignment and Uniformity in Unsupervised Semantic Segmentation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2211.14513