Semantic-Cohesive Knowledge Distillation for Deep Cross-modal Hashing

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Sun, Changchang, Chen, Vickie, Yan, Yan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911203558686720
author Sun, Changchang
Chen, Vickie
Yan, Yan
author_facet Sun, Changchang
Chen, Vickie
Yan, Yan
contents Recently, deep supervised cross-modal hashing methods have achieve compelling success by learning semantic information in a self-supervised way. However, they still suffer from the key limitation that the multi-label semantic extraction process fail to explicitly interact with raw multimodal data, making the learned representation-level semantic information not compatible with the heterogeneous multimodal data and hindering the performance of bridging modality gap. To address this limitation, in this paper, we propose a novel semantic cohesive knowledge distillation scheme for deep cross-modal hashing, dubbed as SODA. Specifically, the multi-label information is introduced as a new textual modality and reformulated as a set of ground-truth label prompt, depicting the semantics presented in the image like the text modality. Then, a cross-modal teacher network is devised to effectively distill cross-modal semantic characteristics between image and label modalities and thus learn a well-mapped Hamming space for image modality. In a sense, such Hamming space can be regarded as a kind of prior knowledge to guide the learning of cross-modal student network and comprehensively preserve the semantic similarities between image and text modality. Extensive experiments on two benchmark datasets demonstrate the superiority of our model over the state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2510_09664
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Semantic-Cohesive Knowledge Distillation for Deep Cross-modal Hashing
Sun, Changchang
Chen, Vickie
Yan, Yan
Machine Learning
Computer Vision and Pattern Recognition
Information Retrieval
Recently, deep supervised cross-modal hashing methods have achieve compelling success by learning semantic information in a self-supervised way. However, they still suffer from the key limitation that the multi-label semantic extraction process fail to explicitly interact with raw multimodal data, making the learned representation-level semantic information not compatible with the heterogeneous multimodal data and hindering the performance of bridging modality gap. To address this limitation, in this paper, we propose a novel semantic cohesive knowledge distillation scheme for deep cross-modal hashing, dubbed as SODA. Specifically, the multi-label information is introduced as a new textual modality and reformulated as a set of ground-truth label prompt, depicting the semantics presented in the image like the text modality. Then, a cross-modal teacher network is devised to effectively distill cross-modal semantic characteristics between image and label modalities and thus learn a well-mapped Hamming space for image modality. In a sense, such Hamming space can be regarded as a kind of prior knowledge to guide the learning of cross-modal student network and comprehensively preserve the semantic similarities between image and text modality. Extensive experiments on two benchmark datasets demonstrate the superiority of our model over the state-of-the-art methods.
title Semantic-Cohesive Knowledge Distillation for Deep Cross-modal Hashing
topic Machine Learning
Computer Vision and Pattern Recognition
Information Retrieval
url https://arxiv.org/abs/2510.09664