CVFeb 10, 2025

Learning Clustering-based Prototypes for Compositional Zero-shot Learning

arXiv:2502.06501v225 citationsh-index: 5ICLR
Originality Incremental advance
AI Analysis

This work addresses the challenge of handling natural diversities in attributes and objects for CZSL, which is incremental as it builds on existing CZSL solutions.

The paper tackles the problem of learning primitive concepts in Compositional Zero-Shot Learning (CZSL) by developing ClusPro, a clustering-based prototype mining framework that outperforms existing methods on three benchmarks under closed-world and open-world settings.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes