用聚类方法发现属性与物体的多样化原型，提升零样本组合识别能力
Learning Clustering-based Prototypes for Compositional Zero-shot Learning
- 通过嵌入空间聚类自动发现并动态更新多个原型，避免单一中心假设
- 在三个基准上超越主流方法，在封闭与开放世界设置下均表现优异
- 无需额外参数或计算开销，适合实际部署的零样本学习场景
从已见组合中学习基础概念（即属性和物体）是组合零样本学习（CZSL）的核心挑战。现有方法通常依赖过于简化的数据假设，例如用单一中心表示每个基本概念，忽略了属性（或物体）在与不同物体（或属性）组合时的自然多样性。本文提出ClusPro，一种基于聚类的原型挖掘框架，通过一组多样化的原型定义基本概念的边界。具体而言，ClusPro在嵌入空间中对同一类基本概念进行聚类，自动发现并动态更新原型。这些代表性原型用于重构结构良好且独立的基本概念嵌入空间，通过基于原型的对比学习与去相关学习实现类内分离与类间解耦。此外，ClusPro以非参数方式高效完成原型聚类，测试阶段不引入额外可学习参数或计算开销。在三个基准上的实验表明，ClusPro在封闭世界与开放世界设置下均优于多种领先方法。
原文摘要 · Abstract (English)
Learning primitive (i.e., attribute and object) concepts from seen compositions is the primary challenge of Compositional Zero-Shot Learning (CZSL). Existing CZSL solutions typically rely on oversimplified data assumptions, e.g., modeling each primitive with a single centroid primitive representation, ignoring the natural diversities of the attribute (resp. object) when coupled with different objects (resp. attribute). In this work, we develop ClusPro, a robust clustering-based prototype mining framework for CZSL that defines the conceptual boundaries of primitives through a set of diversified prototypes. Specifically, ClusPro conducts within-primitive clustering on the embedding space for automatically discovering and dynamically updating prototypes. These representative prototypes are subsequently used to repaint a well-structured and independent primitive embedding space, ensuring intra-primitive separation and inter-primitive decorrelation through prototype-based contrastive learning and decorrelation learning. Moreover, ClusPro efficiently performs prototype clustering in a non-parametric fashion without the introduction of additional learnable parameters or computational budget during testing. Experiments on three benchmarks demonstrate ClusPro outperforms various top-leading CZSL solutions under both closed-world and open-world settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。