Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ning, Hailong, Wang, Siying, Lei, Tao, Cao, Xiaopeng, Dou, Huanmin, Zhao, Bin, Nandi, Asoke K., Radeva, Petia
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908375002906624
author Ning, Hailong
Wang, Siying
Lei, Tao
Cao, Xiaopeng
Dou, Huanmin
Zhao, Bin
Nandi, Asoke K.
Radeva, Petia
author_facet Ning, Hailong
Wang, Siying
Lei, Tao
Cao, Xiaopeng
Dou, Huanmin
Zhao, Bin
Nandi, Asoke K.
Radeva, Petia
contents Remote Sensing Image-Text Retrieval (RSITR) plays a critical role in geographic information interpretation, disaster monitoring, and urban planning by establishing semantic associations between image and textual descriptions. Existing Parameter-Efficient Fine-Tuning (PEFT) methods for Vision-and-Language Pre-training (VLP) models typically adopt symmetric adapter structures for exploring cross-modal correlations. However, the strong discriminative nature of text modality may dominate the optimization process and inhibits image representation learning. The nonnegligible imbalanced cross-modal optimization remains a bottleneck to enhancing the model performance. To address this issue, this study proposes a Representation Discrepancy Bridging (RDB) method for the RSITR task. On the one hand, a Cross-Modal Asymmetric Adapter (CMAA) is designed to enable modality-specific optimization and improve feature alignment. The CMAA comprises a Visual Enhancement Adapter (VEA) and a Text Semantic Adapter (TSA). VEA mines fine-grained image features by Differential Attention (DA) mechanism, while TSA identifies key textual semantics through Hierarchical Attention (HA) mechanism. On the other hand, this study extends the traditional single-task retrieval framework to a dual-task optimization framework and develops a Dual-Task Consistency Loss (DTCL). The DTCL improves cross-modal alignment robustness through an adaptive weighted combination of cross-modal, classification, and exponential moving average consistency constraints. Experiments on RSICD and RSITMD datasets show that the proposed RDB method achieves a 6%-11% improvement in mR metrics compared to state-of-the-art PEFT methods and a 1.15%-2% improvement over the full fine-tuned GeoRSCLIP model.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16756
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval
Ning, Hailong
Wang, Siying
Lei, Tao
Cao, Xiaopeng
Dou, Huanmin
Zhao, Bin
Nandi, Asoke K.
Radeva, Petia
Computer Vision and Pattern Recognition
Information Retrieval
Multimedia
Remote Sensing Image-Text Retrieval (RSITR) plays a critical role in geographic information interpretation, disaster monitoring, and urban planning by establishing semantic associations between image and textual descriptions. Existing Parameter-Efficient Fine-Tuning (PEFT) methods for Vision-and-Language Pre-training (VLP) models typically adopt symmetric adapter structures for exploring cross-modal correlations. However, the strong discriminative nature of text modality may dominate the optimization process and inhibits image representation learning. The nonnegligible imbalanced cross-modal optimization remains a bottleneck to enhancing the model performance. To address this issue, this study proposes a Representation Discrepancy Bridging (RDB) method for the RSITR task. On the one hand, a Cross-Modal Asymmetric Adapter (CMAA) is designed to enable modality-specific optimization and improve feature alignment. The CMAA comprises a Visual Enhancement Adapter (VEA) and a Text Semantic Adapter (TSA). VEA mines fine-grained image features by Differential Attention (DA) mechanism, while TSA identifies key textual semantics through Hierarchical Attention (HA) mechanism. On the other hand, this study extends the traditional single-task retrieval framework to a dual-task optimization framework and develops a Dual-Task Consistency Loss (DTCL). The DTCL improves cross-modal alignment robustness through an adaptive weighted combination of cross-modal, classification, and exponential moving average consistency constraints. Experiments on RSICD and RSITMD datasets show that the proposed RDB method achieves a 6%-11% improvement in mR metrics compared to state-of-the-art PEFT methods and a 1.15%-2% improvement over the full fine-tuned GeoRSCLIP model.
title Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval
topic Computer Vision and Pattern Recognition
Information Retrieval
Multimedia
url https://arxiv.org/abs/2505.16756