Imagen de Portada

Revealing the Semantic Selection Gap in DINOv3 through Training-Free Few-Shot Segmentation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zakir, Hussni Mohd, Ho, Eric Tatt Wei
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Segment Any Class (SAC): Multi-Class Few-Shot Semantic Segmentation via Class Region Proposals
por: Zakir, Hussni Mohd, et al.
Publicado: (2024)

dinov3.seg: Open-Vocabulary Semantic Segmentation with DINOv3
por: Dutta, Saikat, et al.
Publicado: (2026)

RAP: Retrieve, Adapt, and Prompt-Fit for Training-Free Few-Shot Medical Image Segmentation
por: Mao, Zhihao, et al.
Publicado: (2026)

DINOv3 with Test-Time Training for Medical Image Registration
por: Wang, Shansong, et al.
Publicado: (2025)

Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation
por: Tong, Jintao, et al.
Publicado: (2024)

Learnable Prompt for Few-Shot Semantic Segmentation in Remote Sensing Domain
por: Immanuel, Steve Andreas, et al.
Publicado: (2024)

Few Shot Semantic Segmentation: a review of methodologies, benchmarks, and open challenges
por: Catalano, Nico, et al.
Publicado: (2023)

AFANet: Adaptive Frequency-Aware Network for Weakly-Supervised Few-Shot Semantic Segmentation
por: Ma, Jiaqi, et al.
Publicado: (2024)

MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping
por: Fateh, Amirreza, et al.
Publicado: (2024)

Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency
por: Wen, Ziqi, et al.
Publicado: (2026)

Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection
por: Kim, Soopil, et al.
Publicado: (2023)

Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation
por: Tong, Jintao, et al.
Publicado: (2025)

Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation
por: Gui, Guan, et al.
Publicado: (2025)

Few-Shot Medical Image Segmentation with High-Fidelity Prototypes
por: Tang, Song, et al.
Publicado: (2024)

Efficient Masked Attention Transformer for Few-Shot Classification and Segmentation
por: Carrión-Ojeda, Dustin, et al.
Publicado: (2025)

Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation
por: Zhang, Zicheng, et al.
Publicado: (2024)

Like Humans to Few-Shot Learning through Knowledge Permeation of Vision and Text
por: Jia, Yuyu, et al.
Publicado: (2024)

The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentation
por: Liu, Yuhan, et al.
Publicado: (2025)

Learning Hierarchical Orthogonal Prototypes for Generalized Few-Shot 3D Point Cloud Segmentation
por: Zhao, Yifei, et al.
Publicado: (2026)

Mitigating Domain Drift in Multi Species Segmentation with DINOv2: A Cross-Domain Evaluation in Herbicide Research Trials
por: Picon, Artzai, et al.
Publicado: (2025)

Bridging the Semantic Chasm: Synergistic Conceptual Anchoring for Generalized Few-Shot and Zero-Shot OOD Perception
por: Christoforos, Alexandros, et al.
Publicado: (2026)

INSID3: Training-Free In-Context Segmentation with DINOv3
por: Cuttano, Claudia, et al.
Publicado: (2026)

Diffusion Features to Bridge Domain Gap for Semantic Segmentation
por: Ji, Yuxiang, et al.
Publicado: (2024)

DIAGen: Semantically Diverse Image Augmentation with Generative Models for Few-Shot Learning
por: Lingenberg, Tobias, et al.
Publicado: (2024)

Layer-Wise Feature Metric of Semantic-Pixel Matching for Few-Shot Learning
por: Tang, Hao, et al.
Publicado: (2024)

STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
por: Liu, Hongli, et al.
Publicado: (2026)

Less is More: A Closer Look at Semantic-based Few-Shot Learning
por: Zhou, Chunpeng, et al.
Publicado: (2024)

UniFGVC: Universal Training-Free Few-Shot Fine-Grained Vision Classification via Attribute-Aware Multimodal Retrieval
por: Guo, Hongyu, et al.
Publicado: (2025)

Sparsity Outperforms Low-Rank Projections in Few-Shot Adaptation
por: Mrabah, Nairouz, et al.
Publicado: (2025)

Task Consistent Prototype Learning for Incremental Few-shot Semantic Segmentation
por: Xu, Wenbo, et al.
Publicado: (2024)

Transductive Zero-Shot and Few-Shot CLIP
por: Martin, Ségolène, et al.
Publicado: (2024)

Through the Looking Glass: A Dual Perspective on Weakly-Supervised Few-Shot Segmentation
por: Ma, Jiaqi, et al.
Publicado: (2025)

Changes in Gaza: DINOv3-Powered Multi-Class Change Detection for Damage Assessment in Conflict Zones
por: Zheng, Kai, et al.
Publicado: (2025)

DINOv3 Meets YOLO26 for Weed Detection in Vegetable Crops
por: Deng, Boyang, et al.
Publicado: (2026)

Structure-Aware Feature Rectification with Region Adjacency Graphs for Training-Free Open-Vocabulary Semantic Segmentation
por: Huang, Qiming, et al.
Publicado: (2025)

Zero-Training Task-Specific Model Synthesis for Few-Shot Medical Image Classification
por: Qin, Yao, et al.
Publicado: (2025)

PGP-SAM: Prototype-Guided Prompt Learning for Efficient Few-Shot Medical Image Segmentation
por: Yan, Zhonghao, et al.
Publicado: (2025)

Improving 3D Few-Shot Segmentation with Inference-Time Pseudo-Labeling
por: Mozafari, Mohammad, et al.
Publicado: (2024)

Investigating the Semantic Robustness of CLIP-based Zero-Shot Anomaly Segmentation
por: Stangl, Kevin, et al.
Publicado: (2024)

Semantic Segmentation Refiner for Ultrasound Applications with Zero-Shot Foundation Models
por: Indelman, Hedda Cohen, et al.
Publicado: (2024)