Towards Comprehensive Interactive Change Understanding in Remote Sensing: A Large-scale Dataset and Dual-granularity Enhanced VLM

• URL: http://arxiv.org/abs/2509.23105v1
• Date: Sat, 27 Sep 2025 04:28:42 GMT
• Title: Towards Comprehensive Interactive Change Understanding in Remote Sensing: A Large-scale Dataset and Dual-granularity Enhanced VLM
• Authors: Junxiao Xue, Quan Deng, Xuecheng Wu, Kelu Yao, Xinyi Yin, Fei Yu, Wei Zhou, Yanfei Zhong, Yang Liu, Dingkang Yang,
• Abstract summary: ChangeIMTI is a large-scale interactive multi-task instruction dataset for change captioning, binary change classification, change counting, and change localization.<n>We introduce a vision-guided vision-language model (ChangeVG) with dual-granularity awareness for bi-temporal remote sensing images.<n>Our method outperforms the strongest method Semantic-CC by 1.39 points on the comprehensive S*m metric.
• Score: 36.840534360955175
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Remote sensing change understanding (RSCU) is essential for analyzing remote sensing images and understanding how human activities affect the environment. However, existing datasets lack deep understanding and interactions in the diverse change captioning, counting, and localization tasks. To tackle these gaps, we construct ChangeIMTI, a new large-scale interactive multi-task instruction dataset that encompasses four complementary tasks including change captioning, binary change classification, change counting, and change localization. Building upon this new dataset, we further design a novel vision-guided vision-language model (ChangeVG) with dual-granularity awareness for bi-temporal remote sensing images (i.e., two remote sensing images of the same area at different times). The introduced vision-guided module is a dual-branch architecture that synergistically combines fine-grained spatial feature extraction with high-level semantic summarization. These enriched representations further serve as the auxiliary prompts to guide large vision-language models (VLMs) (e.g., Qwen2.5-VL-7B) during instruction tuning, thereby facilitating the hierarchical cross-modal learning. We extensively conduct experiments across four tasks to demonstrate the superiority of our approach. Remarkably, on the change captioning task, our method outperforms the strongest method Semantic-CC by 1.39 points on the comprehensive S*m metric, which integrates the semantic similarity and descriptive accuracy to provide an overall evaluation of change caption. Moreover, we also perform a series of ablation studies to examine the critical components of our method.

Related papers

• Revisiting Multi-Task Visual Representation Learning [52.93947931352643]
  We introduce MTV, a principled multi-task visual pretraining framework.<n>We leverage high-capacity "expert" models to synthesize dense, structured pseudo-labels at scale.<n>Our results demonstrate that MTV achieves "best-of-both-worlds" performance.
  arXiv  Detail & Related papers  (2026-01-20T11:59:19Z)
• SATGround: A Spatially-Aware Approach for Visual Grounding in Remote Sensing [57.609801041296095]
  Vision-language models (VLMs) are emerging as powerful tools for remote sensing.<n>We enhance VLM-based visual grounding in satellite imagery by proposing a novel structured localization mechanism.
  arXiv  Detail & Related papers  (2025-12-09T18:15:43Z)
• Knowledge Transfer from Interaction Learning [16.83991179271622]
  Current visual foundation models (VFMs) face a fundamental limitation in transferring knowledge from vision language models (VLMs)<n>We propose Learning from Interactions (LFI), a cognitive-inspired framework that explicitly modeling visual understanding as an interactive process.
  arXiv  Detail & Related papers  (2025-09-23T07:27:36Z)
• GoViG: Goal-Conditioned Visual Navigation Instruction Generation [69.79110149746506]
  We introduce Goal-Conditioned Visual Navigation Instruction Generation (GoViG), a new task that aims to autonomously generate precise and contextually coherent navigation instructions.<n>GoViG exclusively leverages raw egocentric visual data, substantially improving its adaptability to unseen and unstructured environments.
  arXiv  Detail & Related papers  (2025-08-13T07:05:17Z)
• DeltaVLM: Interactive Remote Sensing Image Change Analysis via Instruction-guided Difference Perception [0.846600473226587]
  We introduce remote sensing image change analysis (RSICA) as a new paradigm that combines the strengths of change detection and visual question answering.<n>We propose DeltaVLM, an end-to-end architecture tailored for interactive RSICA.<n>DeltaVLM features three innovations: (1) a fine-tuned bi-temporal vision encoder to capture temporal differences; (2) a visual difference perception module with a cross-semantic relation measuring mechanism to interpret changes; and (3) an instruction-guided Q-former to effectively extract query-relevant difference information.
  arXiv  Detail & Related papers  (2025-07-30T03:14:27Z)
• Graph Aggregation Prototype Learning for Semantic Change Detection in Remote Sensing [11.262559117458304]
  We propose graph aggregation prototype learning for semantic change detection in remote sensing.<n>Our method achieves state-of-the-art performance, with significant improvements in accuracy and robustness for SCD task.
  arXiv  Detail & Related papers  (2025-07-15T03:03:29Z)
• Remote Sensing Large Vision-Language Model: Semantic-augmented Multi-level Alignment and Semantic-aware Expert Modeling [42.46176089721314]
  Large Vision and Language Models (LVLMs) have shown strong performance across various vision-language tasks in natural image domains.<n>Their application to remote sensing (RS) remains underexplored due to significant domain differences in visual appearances, object scales, and semantics.<n>We propose a novel LVLM framework tailored for RS understanding, incorporating two core components: Semantic-augmented Multi-level Alignment and Semantic-aware Expert Modeling.
  arXiv  Detail & Related papers  (2025-06-27T02:31:37Z)
• From Holistic to Localized: Local Enhanced Adapters for Efficient Visual Instruction Fine-Tuning [102.18178065928426]
  Efficient Visual Instruction Fine-Tuning (EVIT) seeks to adapt Multimodal Large Language Models (MLLMs) to downstream tasks with minimal computational overhead.<n>We propose the Dual Low-Rank Adaptation (Dual-LoRA), a holistic-to-local framework that enhances the adapter's capacity to address data conflict.
  arXiv  Detail & Related papers  (2024-11-19T11:03:09Z)
• 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)
• Semantic-CC: Boosting Remote Sensing Image Change Captioning via Foundational Knowledge and Semantic Guidance [19.663899648983417]
  We introduce a novel change captioning (CC) method based on the foundational knowledge and semantic guidance. We validate the proposed method on the LEVIR-CC and LEVIR-CD datasets.
  arXiv  Detail & Related papers  (2024-07-19T05:07:41Z)
• Position-Aware Contrastive Alignment for Referring Image Segmentation [65.16214741785633]
  We present a position-aware contrastive alignment network (PCAN) to enhance the alignment of multi-modal features. Our PCAN consists of two modules: 1) Position Aware Module (PAM), which provides position information of all objects related to natural language descriptions, and 2) Contrastive Language Understanding Module (CLUM), which enhances multi-modal alignment.
  arXiv  Detail & Related papers  (2022-12-27T09:13:19Z)
• DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention [101.99313208598569]
  Vision-and-language (V-L) tasks require the system to understand both vision content and natural language. We propose DiMBERT (short for Disentangled Multimodal-Attention BERT), which applies separated attention spaces for vision and language. We show that DiMBERT sets new state-of-the-art performance on three tasks.
  arXiv  Detail & Related papers  (2022-10-28T23:00:40Z)
• Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation [87.1188556802942]
  We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. We propose a novel Cross-Task Relation Layer (CTRL), which encodes task dependencies between the semantic and depth predictions. Furthermore, we propose an Iterative Self-Learning (ISL) training scheme, which exploits semantic pseudo-labels to provide extra supervision on the target domain.
  arXiv  Detail & Related papers  (2021-05-17T13:42:09Z)

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.