Hierarchical visual primitive experts for compositional zero-shot learning

H Kim, J Lee, S Park, K Sohn - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Compositional zero-shot learning (CZSL) aims to recognize unseen compositions with prior
knowledge of known primitives (attribute and object). Previous works for CZSL often suffer …

Leveraging sub-class discimination for compositional zero-shot learning

X Hu, Z Wang - Proceedings of the AAAI Conference on Artificial …, 2023 - ojs.aaai.org
Abstract Compositional Zero-Shot Learning (CZSL) aims at identifying unseen compositions
composed of previously seen attributes and objects during the test phase. In real images …

Distilled reverse attention network for open-world compositional zero-shot learning

Y Li, Z Liu, S Jha, L Yao - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Abstract Open-World Compositional Zero-Shot Learning (OW-CZSL) aims to recognize new
compositions of seen attributes and objects. In OW-CZSL, methods built on the conventional …

Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning

Y Li, Z Liu, H Chen, L Yao - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
Abstract Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-
object pairs based on a limited set of observed examples. Current CZSL methodologies …

Simple primitives with feasibility-and contextuality-dependence for open-world compositional zero-shot learning

Z Liu, Y Li, L Yao, X Chang, W Fang… - … on Pattern Analysis …, 2023 - ieeexplore.ieee.org
The task of Open-World Compositional Zero-Shot Learning (OW-CZSL) is to recognize novel
state-object compositions in images from all possible compositions, where the novel …

Procc: Progressive cross-primitive compatibility for open-world compositional zero-shot learning

F Huo, W Xu, S Guo, J Guo, H Wang, Z Liu… - Proceedings of the AAAI …, 2024 - ojs.aaai.org
Open-World Compositional Zero-shot Learning (OW-CZSL) aims to recognize novel
compositions of state and object primitives in images with no priors on the compositional …

A Dynamic Learning Method towards Realistic Compositional Zero-Shot Learning

X Hu, Z Wang - Proceedings of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
To tackle the challenge of recognizing images of unseen attribute-object compositions,
Compositional Zero-Shot Learning (CZSL) methods have been previously addressed …

Contextual Interaction via Primitive-based Adversarial Training For Compositional Zero-shot Learning

S Li, C Jiang, S Wang, Y Long, Z Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
Compositional Zero-shot Learning (CZSL) aims to identify novel compositions via known
attribute-object pairs. The primary challenge in CZSL tasks lies in the significant …

Focusing on valid search space in Open-World Compositional Zero-Shot Learning by leveraging misleading answers.

S Kim, S Lee, YS Choi - IEEE Access, 2024 - ieeexplore.ieee.org
The goal of Compositional Zero-Shot Learning (CZSL) is to recognize various compositions
of state-object pairs. Because the compositions that need to be considered are only a subset …

[PDF][PDF] Continual Compositional Zero-Shot Learning

Y Zhang, S Feng, J Yuan - ijcai.org
Abstract Compositional Zero-Shot Learning (CZSL) aims to recognize unseen compositions
with the knowledge learned from seen compositions, where each composition is composed …