dinov3.seg: Open-Vocabulary Semantic Segmentation with DINOv3

• URL: http://arxiv.org/abs/2603.19531v1
• Date: Thu, 19 Mar 2026 23:57:28 GMT
• Title: dinov3.seg: Open-Vocabulary Semantic Segmentation with DINOv3
• Abstract summary: Open-Vocabulary Semantics (OVSS) assigns pixel-level labels from an open set of text-defined categories, demanding reliable generalization to unseen classes at inference.<n>We introduce dinov3.seg, extending dinov3.txt into a dedicated framework for OVSS.<n>Our contributions are four-fold. First, we design a task-specific architecture tailored to this backbone, systematically adapting established design principles from prior open-vocabulary segmentation work.<n>Second, we jointly leverage text embeddings aligned with both the global [] token and local patch-level visual features from ViT-based encoder
• Score: 36.6036728217708
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Open-Vocabulary Semantic Segmentation (OVSS) assigns pixel-level labels from an open set of text-defined categories, demanding reliable generalization to unseen classes at inference. Although modern vision-language models (VLMs) support strong open-vocabulary recognition, their representations learned through global contrastive objectives remain suboptimal for dense prediction, prompting many OVSS methods to depend on limited adaptation or refinement of image-text similarity maps. This, in turn, restricts spatial precision and robustness in complex, cluttered scenes. We introduce dinov3.seg, extending dinov3.txt into a dedicated framework for OVSS. Our contributions are four-fold. First, we design a task-specific architecture tailored to this backbone, systematically adapting established design principles from prior open-vocabulary segmentation work. Second, we jointly leverage text embeddings aligned with both the global [CLS] token and local patch-level visual features from ViT-based encoder, effectively combining semantic discrimination with fine-grained spatial locality. Third, unlike prior approaches that rely primarily on post hoc similarity refinement, we perform early refinement of visual representations prior to image-text interaction, followed by late refinement of the resulting image-text correlation features, enabling more accurate and robust dense predictions in cluttered scenes. Finally, we propose a high-resolution local-global inference strategy based on sliding-window aggregation, which preserves spatial detail while maintaining global context. We conduct extensive experiments on five widely adopted OVSS benchmarks to evaluate our approach. The results demonstrate its effectiveness and robustness, consistently outperforming current state-of-the-art methods.

Related papers

• Global Graph-Validated Optimization for VLM-based 3D Indoor Scene Generation [15.117449876348774]
  We study open-vocabulary 3D indoor layout generation, synthesizes diverse physically plausible scenes from unlabeled 3D language instructions.<n>Our method achieves state-of-the-art performance in open-vocabulary 3D indoor layout generation.
  arXiv  Detail & Related papers  (2026-08-04T03:24:09Z)
• DINOde: Continuous Vision-Text Alignment for Open-Vocabulary Semantic Segmentation [53.011370226020695]
  We propose DINOde, an ODE-based framework that aligns CLIP text embeddings with the DINO visual manifold.<n>Our approach employs two complementary components: (i) Semantic Text Flow (STF), which evolves text embeddings toward the DINO manifold through a continuous ODE trajectory, and (ii) Global Context Flow (GCF), which refines the holistic image representation carried by DINO's CLS token.<n>By modeling alignment as a continuous trajectory, DINOde avoids the entanglement inherent in discrete projections and yields more robust cross-modal alignment.
  arXiv  Detail & Related papers  (2026-07-23T14:37:27Z)
• Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds [53.82500407523346]
  PointINS is an instance-oriented self-supervised framework that enriches point cloud representations through geometry-aware learning.<n>PointINS achieves on average +3.5% mAP improvement for indoor instance segmentation and +4.1% PQ gain for outdoor panoptic segmentation.
  arXiv  Detail & Related papers  (2026-03-26T08:31:06Z)
• LoGoSeg: Integrating Local and Global Features for Open-Vocabulary Semantic Segmentation [12.192429756057132]
  Open-vocabulary semantic segmentation (OVSS) extends traditional closed-set segmentation by enabling pixel-wise annotation for both seen and unseen categories.<n>LoGoSeg integrates three key innovations: (i) an object existence prior that dynamically weights relevant categories through global image-text similarity, effectively reducing hallucinations; (ii) a region-aware alignment module that establishes precise region-level visual-textual correspondences; and (iii) a dual-stream fusion mechanism that optimally combines local structural information with global semantic context.
  arXiv  Detail & Related papers  (2026-02-05T12:03:11Z)
• LOC: A General Language-Guided Framework for Open-Set 3D Occupancy Prediction [9.311605679381529]
  We propose LOC, a general language-guided framework adaptable to various occupancy networks.<n>For self-supervised tasks, we employ a strategy that fuses multi-frame LiDAR points for dynamic/static scenes, using Poisson reconstruction to fill voids, and assigning semantics to voxels via K-Nearest Neighbor (KNN)<n>Our model predicts dense voxel features embedded in the CLIP feature space, integrating textual and image pixel information, and classifies based on text and semantic similarity.
  arXiv  Detail & Related papers  (2025-10-25T03:27:19Z)
• Plug-in Feedback Self-adaptive Attention in CLIP for Training-free Open-Vocabulary Segmentation [48.488114831677166]
  CLIP exhibits strong visual-textual alignment but struggle with open-vocabulary segmentation due to poor localization.<n>We propose a training-free, feedback-driven self-adaptive framework that adapts output-based patch-level correspondences back to the intermediate attention.
  arXiv  Detail & Related papers  (2025-08-27T20:47:03Z)
• Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models [57.357091028792325]
  Vision-language models (VLMs) pre-trained on web-scale data exhibit promising zero-shot generalization but often suffer from semantic misalignment.<n>We propose a novel constrained prompt enhancement (CPE) method to improve visual-textual alignment.<n>Our approach consists of two key components: Topology-Guided Synonymous Semantic Generation (TGSSG) and Category-Agnostic Discriminative Region Selection (CADRS)
  arXiv  Detail & Related papers  (2025-08-24T15:45:22Z)
• Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception [71.26728044621458]
  DeCLIP is a novel framework that enhances CLIP by decoupling the self-attention module to obtain content'' and context'' features respectively.<n>It consistently achieves state-of-the-art performance across a broad spectrum of tasks, including 2D detection and segmentation, 3D instance segmentation, video instance segmentation, and 6D object pose estimation.
  arXiv  Detail & Related papers  (2025-08-15T06:43:51Z)
• EgoSplat: Open-Vocabulary Egocentric Scene Understanding with Language Embedded 3D Gaussian Splatting [108.15136508964011]
  EgoSplat is a language-embedded 3D Gaussian Splatting framework for open-vocabulary egocentric scene understanding.<n>EgoSplat achieves state-of-the-art performance in both localization and segmentation tasks on two datasets.
  arXiv  Detail & Related papers  (2025-03-14T12:21:26Z)
• GOV-NeSF: Generalizable Open-Vocabulary Neural Semantic Fields [50.68719394443926]
  Generalizable Open-Vocabulary Neural Semantic Fields (GOV-NeSF) is a novel approach offering a generalizable implicit representation of 3D scenes with open-vocabulary semantics. GOV-NeSF exhibits state-of-the-art performance in both 2D and 3D open-vocabulary semantic segmentation.
  arXiv  Detail & Related papers  (2024-04-01T05:19:50Z)
• ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration [48.01536973731182]
  We introduce a new vision-and-language pretraining method called ROSITA. It integrates the cross- and intra-modal knowledge in a unified scene graph to enhance the semantic alignments. ROSITA significantly outperforms existing state-of-the-art methods on three typical vision-and-language tasks over six benchmark datasets.
  arXiv  Detail & Related papers  (2021-08-16T13:16:58Z)

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.