Proxy Zero-Shot Hashing with Multimodal Fusion via Stable Diffusion
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (15) · 12529-12537
DOI: 10.1609/aaai.v40i15.38247 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Hui Zhang und 3 weiteren Autor:innen.
Abstract (Originalsprache)
With the rapid growth of visual content in open-world environments, zero-shot hashing image retrieval (ZSHIR) has emerged to tackle the challenge of recognizing novel classes using attribute-level and semantic information. However, existing methods often rely on shallow fusion of multi-source cues (e.g., attributes, labels, and visual features) through external supervision or feature concatenation, failing to capture the underlying semantic structure in a generative way. Particularly, current bridging strategies between modalities suffer from information fragmentation and weak alignment, hindering the model's ability to fully understand complex attribute-visual relations. Moreover, subtle semantic gaps or “semantic drift” between seen and unseen classes further degrade inter-class separability and the scalability of hashing models. To address these issues, we propose a novel framework called Proxy Zero-Shot Hashing with Multimodal Fusion via Stable Diffusion (PZSH), which integrates generative modeling and contrastive learning. PZSH leverages a pre-trained Stable Diffusion (SD) model to synthesize multimodal content, and uses dual BLIP encoders to enhance semantic alignment across modalities. We further design a proxy hashing loss to enforce discriminative binary representations. Extensive experiments on benchmark datasets show that PZSH achieves state-of-the-art performance with stronger generalization to unseen classes.
Zitieren
APA
Zhang, H., Gao, W., Yang, T., & Cao, Y. (2026). Proxy Zero-Shot Hashing with Multimodal Fusion via Stable Diffusion. Proceedings of the AAAI Conference on Artificial Intelligence, 40(15), 12529-12537. https://doi.org/10.1609/aaai.v40i15.38247
Vancouver
Zhang H, Gao W, Yang T, Cao Y. Proxy Zero-Shot Hashing with Multimodal Fusion via Stable Diffusion. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(15):12529-12537. doi:10.1609/aaai.v40i15.38247
BibTeX
@article{Zhang2026,
author = {Zhang, Hui and Gao, Weikang and Yang, Tao and Cao, Yuan},
title = {Proxy Zero-Shot Hashing with Multimodal Fusion via Stable Diffusion},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {15},
pages = {12529--12537},
doi = {10.1609/aaai.v40i15.38247}
}
EUVIMED