Duplex: Dual Prototype Learning for Compositional Zero-Shot Learning

2025-01-13 · Zhong Peng, Yishi Xu, Gerong Wang, Wenchao Chen, Bo Chen, Jing Zhang

Compositional Zero-Shot Learning (CZSL) aims to enable models to recognize novel compositions of visual states and objects that were absent during training. Existing methods predominantly focus on learning semantic representations of seen compositions but often fail to disentangle the independent features of states and objects in images, thereby limiting their ability to generalize to unseen compositions. To address this challenge, we propose Duplex, a novel dual-prototype learning method that integrates semantic and visual prototypes through a carefully designed dual-branch architecture, enabling effective representation learning for compositional tasks. Duplex utilizes a Graph Neural Network (GNN) to adaptively update visual prototypes, capturing complex interactions between states and objects. Additionally, it leverages the strong visual-semantic alignment of pre-trained Vision-Language Models (VLMs) and employs a multi-path architecture combined with prompt engineering to align image and text representations, ensuring robust generalization. Extensive experiments on three benchmark datasets demonstrate that Duplex outperforms state-of-the-art methods in both closed-world and open-world settings.

📄 PDF Abstract BibTeX arXiv:2501.07114

Code (0)

등록된 구현이 없습니다.

Tasks

Compositional Zero-Shot Learning Graph Neural NetworkLearning Semantic RepresentationsPrompt Engineering Representation Learning Zero-Shot Learning

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Graph Neural Network 설명 없음

Focus 설명 없음

Dual-Modal Prototype Joint Learning for Compositional Zero-Shot Learning

2025-01-23 · Shiyu Zhang, Cheng Yan, Yang Liu, Chenchen Jing 외

Compositional Zero-Shot Learning (CZSL) aims to recognize novel compositions of attributes and objects by leveraging knowledge learned from seen compositions. Recent approaches have explored the use of Vision-Language Mo…

Compositional Zero-Shot Learning Prompt Engineering Zero-Shot Learning

Independent Prototype Propagation for Zero-Shot Compositionality

2021-06-01 · NeurIPS 2021 12 · Frank Ruis, Gertjan Burghouts, Doina Bucur

Humans are good at compositional zero-shot reasoning; someone who has never seen a zebra before could nevertheless recognize one when we tell them it looks like a horse with black and white stripes. Machine learning syst…

Attribute Compositional Zero-Shot Learning

HOMOE: A Memory-Based and Composition-Aware Framework for Zero-Shot Learning with Hopfield Network and Soft Mixture of Experts

2023-11-23 · Do Huu Dat, Po Yuan Mao, Tien Hoang Nguyen, Wray Buntine 외

Compositional Zero-Shot Learning (CZSL) has emerged as an essential paradigm in machine learning, aiming to overcome the constraints of traditional zero-shot learning by incorporating compositional thinking into its meth…

Compositional Zero-Shot Learning Mixture-of-Experts Zero-Shot Learning

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning

2025-06-26 · Xiao Zhang, Yongqiang Ma, Haodong Jing, Nanning Zheng

Compositional Zero-Shot Learning (CZSL) investigates compositional generalization capacity to recognize unknown state-object pairs based on learned primitive concepts. Existing CZSL methods typically derive primitives fe…

Compositional Zero-Shot Learning Mixture-of-Experts Zero-Shot Learning

Learning Clustering-based Prototypes for Compositional Zero-shot Learning

2025-02-10 · Hongyu Qu, Jianan Wei, Xiangbo Shu, Wenguan Wang

Learning primitive (i.e., attribute and object) concepts from seen compositions is the primary challenge of Compositional Zero-Shot Learning (CZSL). Existing CZSL solutions typically rely on oversimplified data assumptio…

Attribute Clustering Compositional Zero-Shot Learning Contrastive Learning+1