Denoised and Dynamic Alignment Enhancement for Zero-Shot Learning
IEEE Transactions on Image Processing · 2025 · 34 · 1501-1515
DOI: 10.1109/tip.2025.3544481 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Jiannan Ge und 6 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 108 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Chinese Academy of Sciences (CAS) Project for Young Scientists in Basic Research.
Abstract (Originalsprache)
Zero-shot learning (ZSL) focuses on recognizing unseen categories by aligning visual features with semantic information. Recent advancements have shown that aligning each attribute with its corresponding visual region significantly improves zero-shot learning performance. However, the crude semantic proxies used in these methods fail to capture the varied appearances of each attribute, and are also easily confused by the presence of semantically redundant backgrounds, leading to suboptimal alignment. To combat these issues, we introduce a novel Alignment-Enhanced Network (AENet), designed to denoise the visual features and dynamically perceive semantic information, thus enhancing visual-semantic alignment. Our approach comprises two key innovations. (1) A visual denoising encoder, employing a class-agnostic mask to filter out semantically redundant visual information, thus producing refined visual features adaptable to unseen classes. (2) A dynamic semantic generator that crafts content-aware semantic proxies adaptively, steered by visual features, enabling AENet to discriminate fine-grained variations in visual contents. Additionally, we integrate a cross-fusion module to ensure comprehensive interaction between the denoised visual features and the generated dynamic semantic proxies, further facilitating visual-semantic alignment. Through extensive experiments across three datasets, the proposed method demonstrates that it narrows down the visual-semantic gap and sets a new benchmark in this setting.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Chinese Academy of Sciences (CAS) Project for Young Scientists in Basic Research
Zitieren
APA
Ge, J., Liu, Z., Li, P., Xie, L., Zhang, Y., Tian, Q., & Xie, H. (2025). Denoised and Dynamic Alignment Enhancement for Zero-Shot Learning. IEEE Transactions on Image Processing, 34, 1501-1515. https://doi.org/10.1109/tip.2025.3544481
Vancouver
Ge J, Liu Z, Li P, Xie L, Zhang Y, Tian Q, et al. Denoised and Dynamic Alignment Enhancement for Zero-Shot Learning. IEEE Transactions on Image Processing. 2025;34:1501-1515. doi:10.1109/tip.2025.3544481
BibTeX
@article{Ge2025,
author = {Ge, Jiannan and Liu, Zhihang and Li, Pandeng and Xie, Lingxi and Zhang, Yongdong and Tian, Qi and Xie, Hongtao},
title = {Denoised and Dynamic Alignment Enhancement for Zero-Shot Learning},
journal = {IEEE Transactions on Image Processing},
year = {2025},
volume = {34},
pages = {1501--1515},
doi = {10.1109/tip.2025.3544481}
}
EUVIMED