DinoSplat-OV is proposed, a training-free framework that adapts DINOv3 to remote sensing without fine-tuning or additional pretraining, effectively filling the gap of DINO-series models in training-free open-vocabulary segmentation and providing a viable new path for further advances in this direction.
Abstract
Remote sensing semantic segmentation is hindered by costly pixel-level annotations, motivating training-free open-vocabulary methods. Recently, the recent release of DINOv3 brings DINO.txt, which equips the standalone DINO backbone with image-text contrastive learning and thus opens up the possibility of open-vocabulary segmentation. We propose DinoSplat-OV, a training-free framework that adapts DINOv3 to remote sensing without fine-tuning or additional pretraining. Targeting the dense distribution, multi-scale nature, and large size of remote sensing imagery, we design two core modules. Its Text-aware Laplacian Propagation module de-noises patch-level predictions by combining textual semantic affinities with local visual similarity, improving regional consistency while preserving boundaries. Its Gaussian Splatting Upsampling module reconstructs pixel-level features through RGB-guided anisotropic aggregation and test-time optimization. A global-anchor sliding-window strategy further supports large-scale imagery. Experiments on UDD5, DOTA, and LoveDA demonstrate competitive or superior performance over existing training-free methods, effectively filling the gap of DINO-series models in training-free open-vocabulary segmentation and providing a viable new path for further advances in this direction.
Vision–language pretrained models, particularly CLIP, have demonstrated remarkable zero-shot transfer capabilities across various image-level tasks, catalyzing the advancement of open-vocabulary semantic segmentation (OVSS) in remote sensing (RS). However, the direct deployment of CLIP to the RS domain is inherently constrained by the profound domain shift between terrestrial and overhead perspectives, as well as the intricate geometric heterogeneities regarding scale and orientation. To circumvent these limitations, we propose CDSeg, a robust framework tailored for RSOVSS. Central to this architecture is the dual-domain feature compensation module (DDFCM), which integrates DINOv3 weights, pretrained on large-scale RS benchmarks, to augment CLIP with domain-specific semantic priors, effectively bridging the natural-to-satellite knowledge gap. Furthermore, we introduce a MambaVision-driven cross-feature fine-grained interaction module (CFFIM) to facilitate a unified refinement of spatial and category attributes, leveraging long-range dependency modeling to enhance the model’s discriminative power in unseen environments. To robustly manage the complexities of diverse orientations and scales, CDSeg incorporates a direction-aware rotation strategy and a wavelet-cross-attention-enhanced module (WCAEM) for high-fidelity multiscale feature decoding. Empirical evaluations on four public benchmarks demonstrate that CDSeg achieves state-of-the-art (SOTA) performance, while extensive ablation studies substantiate the synergistic contribution and indispensability of each component.
Jiayuan Li, Zhen Wang, Xiao Sun et al.· IEEE Transactions on Geoscie...· 0 citations
Referring remote sensing image segmentation (RRSIS) aims to segment target ground objects in high-resolution remote sensing imagery according to textual descriptions. Due to complex backgrounds and large-scale variations, accurately aligning linguistic semantics with spatial regions remains a challenging problem. Existing RRSIS methods are predominantly segmentation-centric, where textual descriptions mainly serve as conditional guidance for pixel-wise prediction rather than explicitly enforcing semantic consistency between visual regions and linguistic representations. This limitation often leads to suboptimal fine-grained alignment and insufficient suppression of background-dominant regions. To address these challenges, we propose a novel RRSIS framework centered on structure-constrained semantic contrastive learning (CL), termed S2CLNet. Departing from the segmentation-driven paradigm, instead of relying solely on segmentation supervision, S2CL introduces region-level structural constraints to perform fine-grained CL in the joint embedding space. This design encourages semantically corresponding visual regions and linguistic representations to be more closely aligned while effectively separating target regions from irrelevant background areas. Furthermore, we develop a dynamic modality balancing module (DMBM) to enhance cross-modal interaction under complex remote sensing scenarios. The DMBM jointly models bidirectional cross-modal attention (BCA) and dynamically adjusts the relative contributions of visual and linguistic modalities according to scene complexity and linguistic specificity, thereby facilitating more adaptive and robust multimodal feature integration. Extensive experiments on three public benchmarks, RefSegRS, RRSIS-D, and RISBench, demonstrate that the proposed method achieves superior performance compared with state-of-the-art approaches. The code will be publicly available at https://github.com/45degreesl
Sen Lei, Shuai Li, Xin-Yu Xiao et al.· IEEE Transactions on Geoscie...· 0 citations
A three-stage framework that integrates complementary priors from Contrastive Language–Image Pre-training, Self-Distillation with No Labels version 2 (DINOv2), and the Segment Anything Model (SAM) is proposed, demonstrating the effectiveness and generalizability of the proposed framework across diverse remote sensing scenarios under image-level supervision.
Remote sensing vision–language models, such as RemoteCLIP and GeoRSCLIP, have advanced image–text representation learning. However, they rely on manually curated caption datasets that are expensive to scale and provide only global image-level supervision. In this paper, we introduce OSM-CLIP, a framework that exploits the freely available, continuously growing annotations of OpenStreetMap (OSM) to provide regionally scalable, patch-level supervision for remote sensing image-text learning. We construct a large-scale dataset of over 265,000 satellite images covering the contiguous United States, each automatically paired with fine-grained geographic annotations scraped from OSM and mapped to individual image patches. A contrastive loss operating at the patch level associates each image region with its corresponding OSM textual description, enabling the model to learn spatially grounded representations without any manual labeling effort. After fine-tuning on standard remote sensing captioning datasets, OSM-CLIP achieves an average improvement of 10.81% in zero-shot classification, 5.06% in text-to-image retrieval (R@1), and 3.87% in image-to-text retrieval (R@1) over existing methods across 13 classification and 4 retrieval benchmarks. Our results demonstrate that freely available geographic annotations can serve as a powerful source of supervision for remote sensing vision–language models in regions with high-quality OSM coverage.
Alessio Pierdominici, R. Ricci, Mohammed Alruqimi et al.· Applied Sciences· 0 citations
Open-vocabulary remote sensing semantic segmentation enables pixel-level recognition of arbitrary semantic categories through text prompts, providing an effective way to reduce the dependence of traditional closed-set remote sensing segmentation on fixed category sets and large-scale annotations. However, existing training-free methods in remote sensing scenarios still mainly rely on local responses and sliding-window inference and thus suffer from insufficient utilization of full-image global semantic priors, unstable local predictions, and unreliable prior propagation. To address these issues, we propose GLoP-SAM3, a dual postprocessing framework for open-vocabulary remote sensing semantic segmentation, whose core idea is to enhance performance through two lightweight postprocessing modules rather than introducing a new backbone or complex trainable components. Specifically, we develop a divergence-aware global–local fusion (DGLF) module, which adaptively integrates full-image semantic priors with local predictions by jointly modeling local–global discrepancy and local confidence, and a reliability-gated prediction refinement (RGPR) module, which suppresses erroneous prior propagation and improves segmentation quality in complex and boundary regions through high-confidence preservation, ambiguous-region enhancement, and prior reliability gating. Built upon SAM3 without any additional training, the proposed method introduces only limited computational overhead while significantly improving prediction consistency and segmentation accuracy. Extensive experiments on eight public remote sensing datasets demonstrate that GLoP-SAM3 consistently improves the baseline and achieves state-of-the-art (SOTA) performance under the training-free setting on representative benchmarks such as OpenEarthMap, validating the favorable balance of the proposed dual postprocessing strategy between efficiency and performance. The code, fixed prompts, and configuration files are available at https://github.com/LiorCohen0901/GLoP-SAM
Chang Liu, Yuzhuo Han, Xiangzhen Kong et al.· IEEE Transactions on Geoscie...· 0 citations
Existing cross-domain few-shot segmentation approaches suffer from high training costs due to source-domain episodic training and pixel-wise dense prediction, while often producing fragmented and noisy predictions. To overcome these issues, we propose a training-free entity-level few-shot segmentation framework for remote sensing images with advection refinement. Specifically, we first leverage SAM3's generic geometric priors to generate category-agnostic entity primitives. By reformulating few-shot inference from pixel-level prediction to entity-level reasoning, foreground and background prototypes are constructed and combined with dense textual semantic responses from SAM3 to build a multi-modal semantic potential field. Furthermore, an advection equation-based semantic refinement mechanism is introduced to propagate category-aware information across both feature and similarity spaces, enhancing semantic continuity and suppressing local texture noise. Extensive experiments on multiple remote sensing datasets demonstrate that the proposed framework effectively mitigates domain shift and local noise, substantially improving SAM3's adaptation capability for remote sensing few-shot segmentation without additional training. Our code will be publicly available at https://github.com/yu-ni1989/ELFSS-AR.
X. Bai, Huan Ni· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
