MAC: A Benchmark for Multiple Attributes Compositional Zero-Shot Learning

arXiv:2406.12757v1 Announce Type: new
Abstract: Compositional Zero-Shot Learning (CZSL) aims to learn semantic primitives (attributes and objects) from seen compositions and recognize unseen attribute-object compositions. Existing CZSL datasets focus on single attributes, neglecting the fact that objects naturally exhibit multiple interrelated attributes. Real-world objects often possess multiple interrelated attributes, and current datasets' narrow attribute scope and single attribute labeling introduce annotation biases, undermining model performance and evaluation. To address these limitations, we introduce the Multi-Attribute Composition (MAC) dataset, encompassing 18,217 …

abstract arxiv attributes benchmark cs.cv current datasets focus learn mac multiple object objects semantic type world zero-shot