论文标题
在无监督语义分段中重新考虑对齐和均匀性
Rethinking Alignment and Uniformity in Unsupervised Semantic Segmentation
论文作者
论文摘要
无监督的图像语义分割（UISS）旨在将低级视觉特征与没有外部监督的语义级别表示。在本文中，我们从特征比对的视图和UISS模型的特征均匀性中介绍了关键属性。我们还对UISS和图像表示学习进行了比较。基于分析，我们认为UIS中现有的基于MI的方法遭受了表示崩溃的影响。通过这种情况，我们提出了一个称为语义注意网络（SAN）的强大网络，其中提出了一个新的模块语义注意（SEAT），以动态地生成像素和语义功能。多个语义分割基准的实验结果表明，我们的无监督分割框架专门捕获语义表示，这表现优于所有未经预告片甚至预计的方法。
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.
