XeMap: Contextual Referring in Large-Scale Remote Sensing Environments

TL;DR

This paper introduces XeMap, a new task and network architecture for precise, context-aware localization of semantic regions in large-scale remote sensing images, addressing limitations of existing methods.

Contribution

The paper proposes the XeMap task, a novel network architecture with multi-scale semantic alignment and a new dataset for large-scale remote sensing scene understanding.

Findings

XeMap-Network outperforms state-of-the-art in zero-shot evaluation.

The hierarchical multi-scale semantic alignment improves localization accuracy.

The new XeMap-set dataset facilitates research in large-scale RS scene interpretation.

Abstract

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.