2026· IEEE Transactions on Geoscience and Remote Sensing· Vol 64, pp. 4414214-4414214· 0 citations· 51 references
Abstract
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.
A lightweight and efficient framework that integrates CLIP and DINO foundation models to address three challenges: semantic misalignment between generic text prompts and RSI-specific visuals; static CAM quality; and incomplete object coverage is proposed.
Xin Li, Nicola Genzano, M. Gianinetto et al.· ISPRS Annals of the Photogra...· 0 citations
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.
Changhao Zhao, Haoxiang Li, Yuke Li et al.· 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.
Abstract. While deep learning has advanced ALS point cloud semantic segmentation and achieved impressive results, most methods rely on predefined label sets and lack ability to recognize arbitrary categories. Recently, the visual foundation models (VFMs) has garnered significant attention, due to remarkable zero-shot generalization capabilities by leveraging open-set knowledge. However, adapting these models to large-scale ALS point clouds remains largely unexplored and highly challenging. In addition, the frequent absence of well-aligned synchronously acquired images further hinders the application of 2D VFMs in ALS point clouds. To bridge these gaps, we developed a zero-shot, open-vocabulary semantic segmentation framework for ALS point clouds based on 2D-3D transfer, utilizing three types of VFMs. We employed a combination of VFMs, including source models pre-trained on natural imagery and models fine-tuned on remote sensing data, to investigate the generalization capabilities of VFMs in inherent domain gap between natural and aerial imagery. Besides, we further introduce an adaptive global view projection module that derives optimal virtual camera poses and field-of-view (FOV) from scene extents, effectively enabling the application of 2D VFMs even in the absence of original imagery. Quantitative evaluations on the Vaihingen dataset indicate that methods trained solely on natural images achieve segmentation accuracy scores of 72% (roof) and 59% (tree) for common classes but struggle with rare categories such as powerline. GSNET improves performance across most categories, highlighting importance of domain adaptation. Evaluation on the SUM dataset reveals that our approach effectively identifies large-scale urban elements (exceeding 60% precision for buildings) without high-quality, well-aligned imagery.
Yanghong Lin, Tianyu Li, Shudong Zhou et al.· The International Archives o...· 1 citation
CROSS is proposed, a tightly integrated paradigm for RRSIS that achieves state-of-the-art performance and maintains precise localization even under severe spatial description perturbations, standing as a robust new paradigm for RRSIS.
Tingzhang Luo, Ruizhong Liu, Yichao Liu et al.· 1 citation
The deployment of large-scale foundation models, such as the Segment Anything Model 3 (SAM 3), promises a transition toward open-vocabulary, training-free computer vision. However, their capacity to generalize out-of-distribution to the complex, top-down geometric structures of Earth Observation imagery remains largely unquantified. Driven by SAM 3's performance disparities in highly specialized domains, we present a comprehensive, multi-task empirical evaluation across remote sensing scene classification, object detection, and instance segmentation under strict zero-shot and one-shot constraints. To achieve this, we introduce a structural adaptation of SAM 3 by repurposing its decoupled binary presence head into a standalone zero-shot classifier. Furthermore, by systematically isolating textual and visual prompt modalities across five configurations, we explicitly diagnose the alignment mechanics within the model's multimodal decoder. Our findings reveal severe cross-modal interference: while visual prompts successfully align the decoder to complex remote sensing geometry, textual prompts inject misaligned, ground-level semantic bias, actively degrading coordinate regression. To benchmark these capabilities without resource-intensive training, we formulate a novel training-free proxy evaluation protocol for Generalized Zero-Shot tasks (scene classification and instance segmentation). Ultimately, our results demonstrate that SAM 3 avoids the overfitting commonly seen in legacy domain-adapted models, achieving high Harmonic Mean scores in segmentation tasks. However, it remains fundamentally constrained by sub-pixel resolution limits and overhead semantic blind spots, charting a definitive mandate for parameter-efficient geospatial fine-tuning of its multimodal decoder.