Learning by Imagining: Debiased Feature Augmentation for Compositional Zero-Shot Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Haozhe, Jing, Chenchen, Liu, Mingyu, Wang, Qingsheng, Chen, Hao
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911157152907264
author Zhang, Haozhe
Jing, Chenchen
Liu, Mingyu
Wang, Qingsheng
Chen, Hao
author_facet Zhang, Haozhe
Jing, Chenchen
Liu, Mingyu
Wang, Qingsheng
Chen, Hao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12711
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning by Imagining: Debiased Feature Augmentation for Compositional Zero-Shot Learning
Zhang, Haozhe
Jing, Chenchen
Liu, Mingyu
Wang, Qingsheng
Chen, Hao
Computer Vision and Pattern Recognition
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.
title Learning by Imagining: Debiased Feature Augmentation for Compositional Zero-Shot Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.12711