Expand-and-Quantize：基于高维空间与乘积量化的无监督语义分割
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization
AI总结：
针对无监督语义分割中降维压缩阻碍聚类的问题，提出结合高维空间聚类与乘积量化压缩的EQUSS框架，在三个基准上达SOTA，并首次从信息论熵角度分析USS特征。
摘要：
无监督语义分割（USS）旨在无需任何标签的情况下发现并识别有意义的类别。成功实现USS需要两项关键能力：1）信息压缩，2）聚类能力。现有方法依赖特征降维实现信息压缩，但该方式可能阻碍聚类过程。本文提出一种名为Expand-and-Quantize Unsupervised Semantic Segmentation（EQUSS，扩展量化无监督语义分割）的新型USS框架，结合了高维空间更优的聚类效果与乘积量化高效的信息压缩优势。大量实验表明，EQUSS在三个标准基准上取得了当前最优结果。此外，本文分析了USS特征的熵，这是从信息论角度理解USS的首次尝试。
英文摘要：
Unsupervised semantic segmentation (USS) aims to discover and recognize meaningful categories without any labels. For a successful USS, two key abilities are required: 1) information compression and 2) clustering capability. Previous methods have relied on feature dimension reduction for information compression, however, this approach may hinder the process of clustering. In this paper, we propose a novel USS framework called Expand-and-Quantize Unsupervised Semantic Segmentation (EQUSS), which combines the benefits of high-dimensional spaces for better clustering and product quantization for effective information compression. Our extensive experiments demonstrate that EQUSS achieves state-of-the-art results on three standard benchmarks. In addition, we analyze the entropy of USS features, which is the first step towards understanding USS from the perspective of information theory.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
