{"ID":2870205,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.12711","arxiv_id":"2509.12711","title":"Learning by Imagining: Debiased Feature Augmentation for Compositional Zero-Shot Learning","abstract":"Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object compositions by learning prior knowledge of seen primitives, \\textit{i.e.}, attributes and objects. Learning generalizable compositional representations in CZSL remains challenging due to the entangled nature of attributes and objects as well as the prevalence of long-tailed distributions in real-world data. Inspired by neuroscientific findings that imagination and perception share similar neural processes, we propose a novel approach called Debiased Feature Augmentation (DeFA) to address these challenges. The proposed DeFA integrates a disentangle-and-reconstruct framework for feature augmentation with a debiasing strategy. DeFA explicitly leverages the prior knowledge of seen attributes and objects by synthesizing high-fidelity composition features to support compositional generalization. Extensive experiments on three widely used datasets demonstrate that DeFA achieves state-of-the-art performance in both \\textit{closed-world} and \\textit{open-world} settings.","short_abstract":"Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object compositions by learning prior knowledge of seen primitives, \\textit{i.e.}, attributes and objects. Learning generalizable compositional representations in CZSL remains challenging due to the entangled nature of attributes and objects as...","url_abs":"https://arxiv.org/abs/2509.12711","url_pdf":"https://arxiv.org/pdf/2509.12711v1","authors":"[\"Haozhe Zhang\",\"Chenchen Jing\",\"Mingyu Liu\",\"Qingsheng Wang\",\"Hao Chen\"]","published":"2025-09-16T06:05:31Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}