XeMap: Contextual Referring in Large-Scale Remote Sensing Environments

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Yuxi, Si, Lu, Hou, Yujie, Liu, Chengaung, Li, Bin, Fang, Hongjian, Zhang, Jun
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913816050139136
author Li, Yuxi
Si, Lu
Hou, Yujie
Liu, Chengaung
Li, Bin
Fang, Hongjian
Zhang, Jun
author_facet Li, Yuxi
Si, Lu
Hou, Yujie
Liu, Chengaung
Li, Bin
Fang, Hongjian
Zhang, Jun
contents Advancements in remote sensing (RS) imagery have provided high-resolution detail and vast coverage, yet existing methods, such as image-level captioning/retrieval and object-level detection/segmentation, often fail to capture mid-scale semantic entities essential for interpreting large-scale scenes. To address this, we propose the conteXtual referring Map (XeMap) task, which focuses on contextual, fine-grained localization of text-referred regions in large-scale RS scenes. Unlike traditional approaches, XeMap enables precise mapping of mid-scale semantic entities that are often overlooked in image-level or object-level methods. To achieve this, we introduce XeMap-Network, a novel architecture designed to handle the complexities of pixel-level cross-modal contextual referring mapping in RS. The network includes a fusion layer that applies self- and cross-attention mechanisms to enhance the interaction between text and image embeddings. Furthermore, we propose a Hierarchical Multi-Scale Semantic Alignment (HMSA) module that aligns multiscale visual features with the text semantic vector, enabling precise multimodal matching across large-scale RS imagery. To support XeMap task, we provide a novel, annotated dataset, XeMap-set, specifically tailored for this task, overcoming the lack of XeMap datasets in RS imagery. XeMap-Network is evaluated in a zero-shot setting against state-of-the-art methods, demonstrating superior performance. This highlights its effectiveness in accurately mapping referring regions and providing valuable insights for interpreting large-scale RS environments.
format Preprint
id arxiv_https___arxiv_org_abs_2505_00738
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle XeMap: Contextual Referring in Large-Scale Remote Sensing Environments
Li, Yuxi
Si, Lu
Hou, Yujie
Liu, Chengaung
Li, Bin
Fang, Hongjian
Zhang, Jun
Image and Video Processing
Machine Learning
Advancements in remote sensing (RS) imagery have provided high-resolution detail and vast coverage, yet existing methods, such as image-level captioning/retrieval and object-level detection/segmentation, often fail to capture mid-scale semantic entities essential for interpreting large-scale scenes. To address this, we propose the conteXtual referring Map (XeMap) task, which focuses on contextual, fine-grained localization of text-referred regions in large-scale RS scenes. Unlike traditional approaches, XeMap enables precise mapping of mid-scale semantic entities that are often overlooked in image-level or object-level methods. To achieve this, we introduce XeMap-Network, a novel architecture designed to handle the complexities of pixel-level cross-modal contextual referring mapping in RS. The network includes a fusion layer that applies self- and cross-attention mechanisms to enhance the interaction between text and image embeddings. Furthermore, we propose a Hierarchical Multi-Scale Semantic Alignment (HMSA) module that aligns multiscale visual features with the text semantic vector, enabling precise multimodal matching across large-scale RS imagery. To support XeMap task, we provide a novel, annotated dataset, XeMap-set, specifically tailored for this task, overcoming the lack of XeMap datasets in RS imagery. XeMap-Network is evaluated in a zero-shot setting against state-of-the-art methods, demonstrating superior performance. This highlights its effectiveness in accurately mapping referring regions and providing valuable insights for interpreting large-scale RS environments.
title XeMap: Contextual Referring in Large-Scale Remote Sensing Environments
topic Image and Video Processing
Machine Learning
url https://arxiv.org/abs/2505.00738