HiSem: Hierarchical Semantic Disentangling for Remote Sensing Image Change Captioning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Man, Liu, Chenyang, Li, Wenjun, Ni, Feng, Jia, Bing, Huang, Baoqi, Xia, Riting, Shi, Zhenwei
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910222132445184
author Wang, Man
Liu, Chenyang
Li, Wenjun
Ni, Feng
Jia, Bing
Huang, Baoqi
Xia, Riting
Shi, Zhenwei
author_facet Wang, Man
Liu, Chenyang
Li, Wenjun
Ni, Feng
Jia, Bing
Huang, Baoqi
Xia, Riting
Shi, Zhenwei
contents Remote sensing image change captioning (RSICC) aims to achieve high-level semantic understanding of genuine changes occurring between bi-temporal images. Despite notable progress, existing methods are fundamentally limited by a shared modeling assumption: changed and unchanged image pairs, which have intrinsically different semantic granularities, are processed under a unified modeling strategy. This modeling inconsistency leads to semantic entanglement between coarse-grained change existence judgment and fine-grained semantic understanding.To address the above limitation, we propose a novel hierarchical semantic disentangling network (HiSem) that explicitly disentangles semantic representations of different granularities. Specifically, we first introduce the Bidirectional Differential Attention Modulation (BDAM) module that leverages discrepancy-aware attention to enhance cross-temporal interactions, thereby amplifying true change signals while suppressing irrelevant variations. Building upon this, we design a Hierarchical Adaptive Semantic Disentanglement (HASD) module that performs adaptive routing at two hierarchical levels: a coarse-grained image-level routing mechanism distinguishes changed and unchanged image pairs, while a fine-grained token-level Mixture-of-Experts (MoE) block models diverse and heterogeneous change semantics for changed samples. Extensive experiments on two benchmark datasets demonstrate that HiSem outperfoms previous methods, achieving a significant improvement of +7.52\% BLEU-4 on the WHU-CDC dataset. More importantly, our approach provides a structured perspective for RSICC by explicitly aligning model design with the intrinsic semantic heterogeneity of bi-temporal scenes. The code will be available at https://github.com/Man-Wang-star/HiSem
format Preprint
id arxiv_https___arxiv_org_abs_2605_15024
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HiSem: Hierarchical Semantic Disentangling for Remote Sensing Image Change Captioning
Wang, Man
Liu, Chenyang
Li, Wenjun
Ni, Feng
Jia, Bing
Huang, Baoqi
Xia, Riting
Shi, Zhenwei
Computer Vision and Pattern Recognition
Remote sensing image change captioning (RSICC) aims to achieve high-level semantic understanding of genuine changes occurring between bi-temporal images. Despite notable progress, existing methods are fundamentally limited by a shared modeling assumption: changed and unchanged image pairs, which have intrinsically different semantic granularities, are processed under a unified modeling strategy. This modeling inconsistency leads to semantic entanglement between coarse-grained change existence judgment and fine-grained semantic understanding.To address the above limitation, we propose a novel hierarchical semantic disentangling network (HiSem) that explicitly disentangles semantic representations of different granularities. Specifically, we first introduce the Bidirectional Differential Attention Modulation (BDAM) module that leverages discrepancy-aware attention to enhance cross-temporal interactions, thereby amplifying true change signals while suppressing irrelevant variations. Building upon this, we design a Hierarchical Adaptive Semantic Disentanglement (HASD) module that performs adaptive routing at two hierarchical levels: a coarse-grained image-level routing mechanism distinguishes changed and unchanged image pairs, while a fine-grained token-level Mixture-of-Experts (MoE) block models diverse and heterogeneous change semantics for changed samples. Extensive experiments on two benchmark datasets demonstrate that HiSem outperfoms previous methods, achieving a significant improvement of +7.52\% BLEU-4 on the WHU-CDC dataset. More importantly, our approach provides a structured perspective for RSICC by explicitly aligning model design with the intrinsic semantic heterogeneity of bi-temporal scenes. The code will be available at https://github.com/Man-Wang-star/HiSem
title HiSem: Hierarchical Semantic Disentangling for Remote Sensing Image Change Captioning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.15024