This paper introduces ProLab, a novel approach using property-level label space for creating strong interpretable segmentation models. Instead of relying solely on category-specific annotations, ProLab uses descriptive properties grounded in common sense knowledge for supervising segmentation models. It is based on two core designs. First, we employ Large Language Models (LLMs) and carefully crafted prompts to generate descriptions of all involved categories that carry meaningful common sense knowledge and follow a structured format. Second, we introduce a description embedding model preserving semantic correlation across descriptions and then cluster them into a set of descriptive properties (e.g., 256) using K-Means. These properties are based on interpretable common sense knowledge consistent with theories of human recognition. We empirically show that our approach makes segmentation models perform stronger on five classic benchmarks (e.g., ADE20K, COCO-Stuff, Pascal Context, Cityscapes, and BDD). Our method also shows better scalability with extended training steps than category-level supervision. Our interpretable segmentation framework also emerges with the generalization ability to segment out-of-domain or unknown categories using only in-domain descriptive properties. Code is available at https://github.com/lambert-x/ProLab.

翻译：本文提出ProLab，一种利用属性级标签空间构建强可解释分割模型的新方法。不同于仅依赖类别特异性标注，ProLab采用基于常识知识的描述性属性来监督分割模型。该方法基于两个核心设计：首先，我们利用大语言模型和精心设计的提示词，生成所有涉及类别的结构化描述，这些描述蕴含丰富的常识知识；其次，我们引入描述嵌入模型以保留描述间的语义相关性，随后通过K-Means聚类将其归并为若干描述性属性集合（例如256个）。这些属性基于与人类识别理论相一致的、可解释的常识知识。实验表明，该方法在五个经典基准测试（如ADE20K、COCO-Stuff、Pascal Context、Cityscapes和BDD）上显著提升了分割模型性能。相较于类别级监督，我们的方法在扩展训练步数时展现出更优的扩展性。所提可解释分割框架还涌现出泛化能力，能够仅凭域内描述性属性对域外或未知类别进行分割。代码开源地址：https://github.com/lambert-x/ProLab。