Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition

2021-08-10 · Ziwei Xu, Guangzhi Wang, Yongkang Wong, Mohan Kankanhalli

This paper proposes a novel model for recognizing images with composite attribute-object concepts, notably for composite concepts that are unseen during model training. We aim to explore the three key properties required by the task --- relation-aware, consistent, and decoupled --- to learn rich and robust features for primitive concepts that compose attribute-object pairs. To this end, we propose the Blocked Message Passing Network (BMP-Net). The model consists of two modules. The concept module generates semantically meaningful features for primitive concepts, whereas the visual module extracts visual features for attributes and objects from input images. A message passing mechanism is used in the concept module to capture the relations between primitive concepts. Furthermore, to prevent the model from being biased towards seen composite concepts and reduce the entanglement between attributes and objects, we propose a blocking mechanism that equalizes the information available to the model for both seen and unseen concepts. Extensive experiments and ablation studies on two benchmarks show the efficacy of the proposed model.

📄 PDF Abstract BibTeX arXiv:2108.04603

Code (1)

daoyuan98/relation-czsl 공식 구현 pytorch

Tasks

AttributeBlocking Compositional Zero-Shot LearningRelationZero-Shot Learning

SalientFusion: Context-Aware Compositional Zero-Shot Food Recognition

2025-09-04 · Jiajun Song, Xiaoou Liu arxiv

Food recognition has gained significant attention, but the rapid emergence of new dishes requires methods for recognizing unseen food categories, motivating Zero-Shot Food Learning (ZSFL). We propose the task of Composit…

Compositional Zero-Shot Learning

Beyond Seen Primitive Concepts and Attribute-Object Compositional Learning

2024-01-01 · CVPR 2024 1 · Nirat Saini, Khoi Pham, Abhinav Shrivastava

Learning from seen attribute-object pairs to generalize to unseen compositions has been studied extensively in Compositional Zero-Shot Learning (CZSL). However CZSL setup is still limited to seen attributes and objec…

Attribute Compositional Zero-Shot Learning Zero-Shot Learning

Attention Based Simple Primitives for Open World Compositional Zero-Shot Learning

2024-07-18 · Ans Munir, Faisal Z. Qureshi, Muhammad Haris Khan, Mohsen Ali

Compositional Zero-Shot Learning (CZSL) aims to predict unknown compositions made up of attribute and object pairs. Predicting compositions unseen during training is a challenging task. We are exploring Open World Compos…

Attribute Compositional Zero-Shot Learning Object Zero-Shot Learning

Structure-aware Prompt Adaptation from Seen to Unseen for Open-Vocabulary Compositional Zero-Shot Learning

2026-03-04 · Yihang Duan, Jiong Wang, Pengpeng Zeng, Ji Zhang 외 arxiv

The goal of Open-Vocabulary Compositional Zero-Shot Learning (OV-CZSL) is to recognize attribute-object compositions in the open-vocabulary setting, where compositions of both seen and unseen attributes and objects are e…

Compositional Zero-Shot Learning

Prompt-Based Continual Compositional Zero-Shot Learning

2025-12-09 · Sauda Maryam, Sara Nadeem, Faisal Qureshi, Mohsen Ali arxiv

We tackle continual adaptation of vision-language models to new attributes, objects, and their compositions in Compositional Zero-Shot Learning (CZSL), while preventing forgetting of prior knowledge. Unlike classical con…

Compositional Zero-Shot Learning Continual Learning