.png){kind=icon}
返回
Semantically guided dynamic visual prototype refinement for compositional zero-shot learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2026.132775.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Compositional Zero-Shot Learning (CZSL) seeks to recognize unseen state–object pairs by recombining primitives learned from seen compositions. Despite recent progress with vision–language models (VLMs), two limitations remain: (i) text-driven semantic prototypes are weakly discriminative in the visual feature space; and (ii) unseen pairs are optimized passively, thereby inducing seen bias. To address these limitations, we present Duplex, a framework that couples dual-prototype learning with dynamic local-graph refinement of visual prototypes. For each composition, Duplex maintains a semantic prototype via prompt learning and a visual prototype for unseen pairs constructed by recombining disentangled state and object primitives from seen images. The visual prototypes are updated dynamically through lightweight aggregation on mini-batch local graphs, which incorporate unseen compositions during training without labels. This design introduces fine-grained visual evidence while preserving semantic structure. It enriches class prototypes, better disambiguates semantically similar yet visually distinct pairs, and mitigates seen bias. Experiments on MIT-States, UT-Zappos, and CGQA in closed-world and open-world settings achieve competitive performance and consistent compositional generalization.
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Preserving text space integrity for robust compositional zero-shot learning via mixture of pretrained experts通过混合预训练的专家来保持文本空间的完整性，以实现强大的组成零射击学习.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Human-like systematic generalization through a meta-learning neural network通过元学习神经网络实现类似人的系统泛化Nature
OAAI
NatureIF0
OAAI分享收藏Exploring inter-and intra-modal relations in compositional zero-shot learning探索跨模态与内模态关系在组合零样本学习中的应用NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
查看更多内容