Work

Enhancing zero-shot scene recognition through semantic autoencoders and visual relation transfer

Year: 2025

Type: article

Abstract: Zero-shot learning enables the recognition of images from unseen classes by leveraging auxiliary semantic information. Traditional methods typically learn either the relationship between the visual features and the semantic vectors or that between the seen and the unseen semantic vectors. However, their zero-shot recognition performances are not ideal for scene images due to large intra-class variations. To address this challenge, we propose a novel approach combining semantic autoencoders (SAEs) and visual relation transfer (VRT), termed SAEVRT. Specifically, we learn two semantic autoencoders for both the seen and the unseen scene classes, which help to alleviate the domain shift between the visual and the semantic spaces. Considering that semantic vectors (no attribute vectors available) are less effective than visual features for scene images, we propose an interpretable seen and unseen visual relation transfer method to learn more effective unseen semantic vectors. By combining SAEs and VRT in a unified learning framework, we exploit both the visual-semantic and seen-unseen relationships. Extensive experiments on four scene datasets demonstrate the superior performance of SAEVRT, achieving recognition accuracies of 63.77%, 67.75%, 58.68%, and 53.26% on Scene15, MIT67, UCM21, and NWPU45, respectively.

Source: Scientific Reports

DOI: 10.1038/s41598-025-28158-4

Authors: Chen Wang, Man Wang, Guohua Peng, Bernard De Baets, Xiong Pan

Institutions: Wuhan Textile University, Northwestern Polytechnical University, Ghent University

Language: English

Topic: Domain Adaptation and Few-Shot Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,690

Funders: National Natural Science Foundation of China, Natural Science Foundation of Hubei Province, Vlaamse regering