Semantic-Driven Scale and Spatial Selection for Efficient Cross-Modal Alignment in Referring Remote Sensing Image Segmentation

• URL: http://arxiv.org/abs/2606.30244v1
• Date: Mon, 29 Jun 2026 12:54:10 GMT
• Title: Semantic-Driven Scale and Spatial Selection for Efficient Cross-Modal Alignment in Referring Remote Sensing Image Segmentation
• Abstract summary: Referring Remote Sensing Image seeks to localize and segment the target object or region specified by a natural language expression in a remote sensing image.<n>Existing RRSIS models have benefited from large-scale foundation models, but they predominantly rely on full fine-tuning.<n>We propose a novel framework, Semantic-driven Scale and Spatial Selection for Efficient Cross-modal Alignment.
• Score: 14.492779733437082
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Referring Remote Sensing Image Segmentation (RRSIS) seeks to localize and segment the target object or region specified by a natural language expression in a remote sensing image. While existing RRSIS models have benefited from large-scale foundation models, they predominantly rely on full fine-tuning. These approaches are computationally intensive and may weaken the generalization ability of pre-trained models, as extensive fine-tuning on significantly smaller downstream datasets can distort the well-structured feature representations learned during large-scale pre-training. Although Parameter-Efficient Tuning (PET) offers a potential alternative, existing PET frameworks primarily focus on single-modal optimization, failing to capture the complex cross-modal dependencies required for multimodal reasoning, while simultaneously struggling to bridge the substantial domain gap between natural scenes and aerial imagery. To address these limitations, we propose a novel framework, Semantic-driven Scale and Spatial Selection for Efficient Cross-modal Alignment (S4ECA), which enables effective and efficient cross-modal interaction through parameter-efficient adaptation. Specifically, we design a dual-encoder adapter architecture. The textual adapter employs learnable queries to distill highly semantic language proxies from word-level embeddings, facilitating early grounding. Simultaneously, the visual adapter refines hierarchical feature representations through a multi-scale dense extractor, followed by a language-guided scale and spatial selection mechanism that dynamically emphasizes relevant visual contexts, ensuring precise cross-modal alignment. By updating only 2.4% of the backbone parameters, our proposed model achieves state-of-the-art performance on the RRSIS-D and RefSegRS datasets, demonstrating superior efficiency and precision in complex aerial scenarios.

Related papers

• ExACT: Exemplar-Driven Calibrated Refinement for Training-Free Visual Grounding in Remote Sensing Images [51.53960096934913]
  Remote sensing visual grounding (RSVG) aims to locate specific objects in high-resolution RS imagery using free-form natural language descriptions.<n>Recent advances in multimodal large language models (MLLMs) show great potential for such open-vocabulary RSVG.<n>We propose Exemplar-driven Calibrated Refinement (ExACT), a training-free framework driven by a one-shot visual prompting mechanism.
  arXiv  Detail & Related papers  (2026-06-27T13:50:39Z)
• RSICCLLM: A Multimodal Large Language Model for Remote Sensing Image Change Captioning [49.24254347822435]
  Remote Sensing Image Change Captioning (RSICC) aims to describe changes between bi-temporal remote sensing images.<n>We propose RSICCLLM, the first post-training framework for large vision-language models in RSICC.
  arXiv  Detail & Related papers  (2026-06-26T16:57:40Z)
• Spatio-Semantic Expert Routing Architecture with Mixture-of-Experts for Referring Image Segmentation [0.3437656066916039]
  Referring image segmentation aims to produce a pixel-level mask for the image region described by a natural-language expression.<n>We propose SERA, a Spatio-Semantic Expert Routing Architecture for referring image segmentation.<n> SERA introduces lightweight, expression-aware expert refinement at two complementary stages within a vision-language framework.
  arXiv  Detail & Related papers  (2026-03-13T00:37:20Z)
• Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models [84.78794648147608]
  A persistent geometric anomaly, the Modality Gap, remains.<n>Prior approaches to bridge this gap are largely limited by oversimplified isotropic assumptions.<n>We propose the Fixed-frame Modality Gap Theory, which decomposes the modality gap into stable biases and anisotropic residuals.<n>We then introduce ReAlign, a training-free modality alignment strategy.
  arXiv  Detail & Related papers  (2026-02-02T13:59:39Z)
• DiffRIS: Enhancing Referring Remote Sensing Image Segmentation with Pre-trained Text-to-Image Diffusion Models [9.109484087832058]
  DiffRIS is a novel framework that harnesses the semantic understanding capabilities of pre-trained text-to-image diffusion models for RRSIS tasks.<n>Our framework introduces two key innovations: a context perception adapter (CP-adapter) and a cross-modal reasoning decoder (PCMRD)
  arXiv  Detail & Related papers  (2025-06-23T02:38:56Z)
• Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval [15.503629941274621]
  This study proposes a Representation Discrepancy Bridging (RDB) method for the Remote Image-Text Retrieval (RSITR) task.<n>Experiments on RSICD and RSITMD datasets show that the proposed RDB method achieves a 6%-11% improvement in mR metrics.
  arXiv  Detail & Related papers  (2025-05-22T14:59:30Z)
• Scale-wise Bidirectional Alignment Network for Referring Remote Sensing Image Segmentation [12.893224628061516]
  The goal of referring remote sensing image segmentation (RRSIS) is to extract specific pixel-level regions within an aerial image via a natural language expression.<n>We propose an innovative framework called Scale-wise Bidirectional Alignment Network (SBANet) to address these challenges.<n>Our proposed method achieves superior performance in comparison to previous state-of-the-art methods on the RRSIS-D and RefSegRS datasets.
  arXiv  Detail & Related papers  (2025-01-01T14:24:04Z)
• Cross-Modal Bidirectional Interaction Model for Referring Remote Sensing Image Segmentation [50.433911327489554]
  The goal of referring remote sensing image segmentation (RRSIS) is to generate a pixel-level mask of the target object identified by the referring expression.<n>To address the aforementioned challenges, a novel RRSIS framework is proposed, termed the cross-modal bidirectional interaction model (CroBIM)<n>To further forster the research of RRSIS, we also construct RISBench, a new large-scale benchmark dataset comprising 52,472 image-language-label triplets.
  arXiv  Detail & Related papers  (2024-10-11T08:28:04Z)
• Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation [63.15257949821558]
  Referring Remote Sensing Image (RRSIS) is a new challenge that combines computer vision and natural language processing. Traditional Referring Image (RIS) approaches have been impeded by the complex spatial scales and orientations found in aerial imagery. We introduce the Rotated Multi-Scale Interaction Network (RMSIN), an innovative approach designed for the unique demands of RRSIS.
  arXiv  Detail & Related papers  (2023-12-19T08:14:14Z)
• Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion [62.269219152425556]
  segmentation-based scene text detection methods have drawn extensive attention in the scene text detection field. We propose a Differentiable Binarization (DB) module that integrates the binarization process into a segmentation network. An efficient Adaptive Scale Fusion (ASF) module is proposed to improve the scale robustness by fusing features of different scales adaptively.
  arXiv  Detail & Related papers  (2022-02-21T15:30:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.