OpenDPR: Open-Vocabulary Change Detection via Vision-Centric Diffusion-Guided Prototype Retrieval for Remote Sensing Imagery

• URL: http://arxiv.org/abs/2603.27645v1
• Date: Sun, 29 Mar 2026 11:43:02 GMT
• Title: OpenDPR: Open-Vocabulary Change Detection via Vision-Centric Diffusion-Guided Prototype Retrieval for Remote Sensing Imagery
• Abstract summary: Open-vocabulary change detection (OVCD) seeks to recognize arbitrary changes of interest by enabling generalization beyond a fixed set of predefined classes.<n>We reformulate OVCD as a two-stage pipeline: first generate class-agnostic change proposals using visual foundation models (VFMs) such as SAM and DINOv2, and then perform category identification with vision-language models (VLMs) such as CLIP.<n>We propose OpenDPR, a training-free vision-centric diffusion-guided prototype retrieval framework.
• Score: 22.361232756908095
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Open-vocabulary change detection (OVCD) seeks to recognize arbitrary changes of interest by enabling generalization beyond a fixed set of predefined classes. We reformulate OVCD as a two-stage pipeline: first generate class-agnostic change proposals using visual foundation models (VFMs) such as SAM and DINOv2, and then perform category identification with vision-language models (VLMs) such as CLIP. We reveal that category identification errors are the primary bottleneck of OVCD, mainly due to the limited ability of VLMs based on image-text matching to represent fine-grained land-cover categories. To address this, we propose OpenDPR, a training-free vision-centric diffusion-guided prototype retrieval framework. OpenDPR leverages diffusion models to construct diverse prototypes for target categories offline, and to perform similarity retrieval with change proposals in the visual space during inference. The secondary bottleneck lies in change localization, due to the inherent lack of change priors in VFMs. To bridge this gap, we design a spatial-to-change weakly supervised change detection module named S2C to adapt their strong spatial modeling capabilities for change localization. Integrating the pretrained S2C into OpenDPR leads to an optional weakly supervised variant named OpenDPR-W, which further improves OVCD with minimal supervision. Experimental results on four benchmark datasets demonstrate that the proposed methods achieve state-of-the-art performance under both supervision modes. Code is available at https://github.com/guoqi2002/OpenDPR.

Related papers

• Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images [48.646448077284276]
  We propose Spatial-FAD, a framework for effective few-shot medical anomaly detection.<n>It improves lesion localization by combining VFM spatial priors with CLIP semantics.<n>Our method achieves an average improvement of over 11.4% in Dice score and 1.8% in AUC.
  arXiv  Detail & Related papers  (2026-09-11T05:21:01Z)
• Cross-Modal Semantic-Enhanced Diffusion Framework for Diabetic Retinopathy Grading [7.923081487850825]
  We propose a vision-language model tailored for diabetic retinopathy (DR) grading as the semantic guidance module.<n>We construct a cross-modal semantic conditioning vector by computing the dot product between image features and the text description features of each DR grade.<n> Experiments on the APTOS 2019 dataset demonstrate that the proposed approach achieves an accuracy of 87.5% and a macro-averaged F1 score of 0.731, outperforming a variety of representative methods.
  arXiv  Detail & Related papers  (2026-05-10T00:58:17Z)
• Seg2Change: Adapting Open-Vocabulary Semantic Segmentation Model for Remote Sensing Change Detection [5.3514684920696824]
  Existing change detection methods are limited to predefined classes in training datasets.<n>We propose Seg2Change, an adapter designed to adapt open-vocabulary semantic segmentation models to change detection task.<n>Our framework achieves state-of-the-art OVCD performance.
  arXiv  Detail & Related papers  (2026-04-13T09:35:14Z)
• GazeCLIP: Gaze-Guided CLIP with Adaptive-Enhanced Fine-Grained Language Prompt for Deepfake Attribution and Detection [80.12497948980378]
  Current deepfake attribution or deepfake detection works tend to exhibit poor generalization to novel generative methods.<n>We propose a novel gaze-guided CLIP with adaptive-enhanced fine-grained language prompts for fine-grained deepfake attribution and detection (DFAD)<n>We conduct a novel and fine-grained benchmark to evaluate the DFAD performance of networks on novel generators like diffusion and flow models.<n>We introduce a gaze-aware model based on CLIP, which is devised to enhance the generalization to unseen face forgery attacks.
  arXiv  Detail & Related papers  (2026-03-31T05:59:59Z)
• OmniOVCD: Streamlining Open-Vocabulary Change Detection with SAM 3 [19.94566126701934]
  Open-Vocabulary Change Detection (OVCD) aims to reduce the reliance on predefined categories.<n>In this paper, we propose OmniOVCD, a standalone framework designed for OVCD.<n>Experiments on four public benchmarks demonstrate SOTA performance, achieving IoU scores of 67.2, 66.5, 24.5, and 27.1 (class-average)
  arXiv  Detail & Related papers  (2026-01-20T12:25:41Z)
• UniVCD: A New Method for Unsupervised Change Detection in the Open-Vocabulary Era [0.0]
  Change detection (CD) identifies scene changes from multi-temporal observations and is widely used in urban development and environmental monitoring.<n>Most existing CD methods rely on supervised learning, making performance strongly dataset-dependent and incurring high annotation costs.<n>We propose Unified Open-Vocabulary Change Detection (UniVCD), an unsupervised, open-vocabulary change detection method built on frozen SAM2 and CLIP.
  arXiv  Detail & Related papers  (2025-12-15T08:42:23Z)
• Referring Change Detection in Remote Sensing Imagery [49.841833753558575]
  We introduce Referring Change Detection (RCD), which leverages natural language prompts to detect specific classes of changes in remote sensing images.<n>We propose a two-stage framework consisting of (I) textbfRCDNet, a cross-modal fusion network designed for referring change detection, and (II) textbfRCDGen, a diffusion-based synthetic data generation pipeline.
  arXiv  Detail & Related papers  (2025-12-12T16:57:12Z)
• Hierarchical Identity Learning for Unsupervised Visible-Infrared Person Re-Identification [81.3063589622217]
  Unsupervised visible-infrared person re-identification (USVI-ReID) aims to learn modality-invariant image features from unlabeled cross-modal person datasets.
  arXiv  Detail & Related papers  (2025-09-15T05:10:43Z)
• DiffVein: A Unified Diffusion Network for Finger Vein Segmentation and Authentication [50.017055360261665]
  We introduce DiffVein, a unified diffusion model-based framework which simultaneously addresses vein segmentation and authentication tasks. For better feature interaction between these two branches, we introduce two specialized modules. In this way, our framework allows for a dynamic interplay between diffusion and segmentation embeddings.
  arXiv  Detail & Related papers  (2024-02-03T06:49:42Z)
• Segment Change Model (SCM) for Unsupervised Change detection in VHR Remote Sensing Images: a Case Study of Buildings [24.520190873711766]
  We propose an unsupervised Change Detection (CD) method named Segment Change Model (SCM) Our method recalibrates features extracted at different scales and integrates them in a top-down manner to enhance discriminative change edges.
  arXiv  Detail & Related papers  (2023-12-27T04:47:03Z)
• Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection [76.11864242047074]
  We propose a novel Affine-Consistent Transformer (AC-Former), which directly yields a sequence of nucleus positions. We introduce an Adaptive Affine Transformer (AAT) module, which can automatically learn the key spatial transformations to warp original images for local network training. Experimental results demonstrate that the proposed method significantly outperforms existing state-of-the-art algorithms on various benchmarks.
  arXiv  Detail & Related papers  (2023-10-22T02:27:02Z)
• HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning [74.76431541169342]
  Zero-shot learning (ZSL) tackles the unseen class recognition problem, transferring semantic knowledge from seen classes to unseen ones. We propose a novel hierarchical semantic-visual adaptation (HSVA) framework to align semantic and visual domains. Experiments on four benchmark datasets demonstrate HSVA achieves superior performance on both conventional and generalized ZSL.
  arXiv  Detail & Related papers  (2021-09-30T14:27:50Z)
• Cross-Modality Brain Tumor Segmentation via Bidirectional Global-to-Local Unsupervised Domain Adaptation [61.01704175938995]
  In this paper, we propose a novel Bidirectional Global-to-Local (BiGL) adaptation framework under a UDA scheme. Specifically, a bidirectional image synthesis and segmentation module is proposed to segment the brain tumor. The proposed method outperforms several state-of-the-art unsupervised domain adaptation methods by a large margin.
  arXiv  Detail & Related papers  (2021-05-17T10:11:45Z)

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.