Rethinking Alignment and Uniformity in Unsupervised Image Semantic Segmentation
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.
First ; Corresponding
National Key Research and Development Program of China[2021YFF1200800];National Natural Science Foundation of China;
|Document Type||Conference paper|
1.Southern University of Science and Technology,China
2.Peng Cheng Laboratory,China
3.Ping An Technology (Shenzhen) Co.,Ltd.,China
|First Author Affilication||Southern University of Science and Technology|
|Corresponding Author Affilication||Southern University of Science and Technology|
|First Author's First Affilication||Southern University of Science and Technology|
Zhang，Daoan,Li，Chenming,Li，Haoquan,et al. Rethinking Alignment and Uniformity in Unsupervised Image Semantic Segmentation[C],2023:11192-11200.
|Files in This Item:||There are no files associated with this item.|
|Recommend this item|
|Export to Endnote|
|Export to Excel|
|Export to Csv|
|Similar articles in Google Scholar|
|Similar articles in Baidu Scholar|
|Similar articles in Bing Scholar|
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.