Image de couverture de livre

DSU-Net:An Improved U-Net Model Based on DINOv2 and SAM2 with Multi-scale Cross-model Feature Enhancement

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xu, Yimin, Yang, Fan, Xu, Bin
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

DSU-Net: Dynamic Snake U-Net for 2-D Seismic First Break Picking
par: Wang, Hongtao, et autres
Publié: (2024)

SLP-Net:An efficient lightweight network for segmentation of skin lesions
par: Yang, Bo, et autres
Publié: (2023)

MDU-Net: Multi-scale Densely Connected U-Net for biomedical image segmentation
par: Zhang, Jiawei, et autres
Publié: (2018)

From SAM to DINOv2: Towards Distilling Foundation Models to Lightweight Baselines for Generalized Polyp Segmentation
par: Agnihotri, Shivanshu, et autres
Publié: (2025)

DINOv2: Learning Robust Visual Features without Supervision
par: Oquab, Maxime, et autres
Publié: (2023)

U-MAN: U-Net with Multi-scale Adaptive KAN Network for Medical Image Segmentation
par: Huang, Bohan, et autres
Publié: (2025)

Synergistic Foundation Models for Semi-Supervised Fetal Cardiac Ultrasound Analysis: SAM-Med2D Boundary Refinement and DINOv3 Semantic Enhancement
par: Zhuang, Tonghao, et autres
Publié: (2026)

ODC-SA Net: Orthogonal Direction Enhancement and Scale Aware Network for Polyp Segmentation
par: Xu, Chenhao, et autres
Publié: (2024)

Leveraging Foundation Models via Knowledge Distillation in Multi-Object Tracking: Distilling DINOv2 Features to FairMOT
par: Faber, Niels G., et autres
Publié: (2024)

FSCA-Net: Feature-Separated Cross-Attention Network for Robust Multi-Dataset Training
par: Chen, Yuehai
Publié: (2026)

LU2Net: A Lightweight Network for Real-time Underwater Image Enhancement
par: Yang, Haodong, et autres
Publié: (2024)

FusionNet: Multi-model Linear Fusion Framework for Low-light Image Enhancement
par: Shi, Kangbiao, et autres
Publié: (2025)

How Universal Are SAM2 Features?
par: Atani, Masoud Khairi, et autres
Publié: (2025)

DINOv2 Driven Gait Representation Learning for Video-Based Visible-Infrared Person Re-identification
par: Yang, Yujie, et autres
Publié: (2025)

Multi-Layer Feature Fusion with Cross-Channel Attention-Based U-Net for Kidney Tumor Segmentation
par: Neha, Fnu, et autres
Publié: (2024)

AMD-HookNet++: Evolution of AMD-HookNet with Hybrid CNN-Transformer Feature Enhancement for Glacier Calving Front Segmentation
par: Wu, Fei, et autres
Publié: (2025)

V$^{2}$-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence
par: Pan, Jiancheng, et autres
Publié: (2025)

U-REPA: Aligning Diffusion U-Nets to ViTs
par: Tian, Yuchuan, et autres
Publié: (2025)

Benchmarking DINOv3 for Multi-Task Stroke Analysis on Non-Contrast CT
par: Zhang, Donghao, et autres
Publié: (2025)

FlexiCrackNet: A Flexible Pipeline for Enhanced Crack Segmentation with General Features Transfered from SAM
par: Wan, Xinlong, et autres
Publié: (2025)

Dynamic U-Net: Adaptively Calibrate Features for Abdominal Multi-organ Segmentation
par: Yang, Jin, et autres
Publié: (2024)

Corner2Net: Detecting Objects as Cascade Corners
par: Liu, Chenglong, et autres
Publié: (2024)

BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-task Dense Predictions
par: Zhang, Jingdong, et autres
Publié: (2023)

Rethinking Cross-Generator Image Forgery Detection through DINOv3
par: Huang, Zhenglin, et autres
Publié: (2025)

M3S-Net: Multimodal Feature Fusion Network Based on Multi-scale Data for Ultra-short-term PV Power Forecasting
par: Niu, Penghui, et autres
Publié: (2026)

Rethinking Transfer Learning for Industrial Inspection: DINOv3 vs. ImageNet Pretraining Across RGB and X-ray Tasks
par: Gharbage, Mehdi, et autres
Publié: (2026)

RCDINO: Enhancing Radar-Camera 3D Object Detection with DINOv2 Semantic Features
par: Matykina, Olga, et autres
Publié: (2025)

SINDER: Repairing the Singular Defects of DINOv2
par: Wang, Haoqi, et autres
Publié: (2024)

Multi-encoder nnU-Net outperforms transformer models with self-supervised pretraining
par: Otaghsara, Seyedeh Sahar Taheri, et autres
Publié: (2025)

General Purpose Image Encoder DINOv2 for Medical Image Registration
par: Song, Xinrui, et autres
Publié: (2024)

Improving U-Net Confidence on TEM Image Data with L2-Regularization, Transfer Learning, and Deep Fine-Tuning
par: Ochoa, Aiden, et autres
Publié: (2025)

CTA-Net: A CNN-Transformer Aggregation Network for Improving Multi-Scale Feature Extraction
par: Meng, Chunlei, et autres
Publié: (2024)

RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection
par: Zhang, Ximiao, et autres
Publié: (2024)

DuInNet: Dual-Modality Feature Interaction for Point Cloud Completion
par: Liu, Xinpu, et autres
Publié: (2024)

ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce Connections
par: Ju, Rui-Yang, et autres
Publié: (2022)

NeuroVascU-Net: A Unified Multi-Scale and Cross-Domain Adaptive Feature Fusion U-Net for Precise 3D Segmentation of Brain Vessels in Contrast-Enhanced T1 MRI
par: Vayeghan, Mohammad Jafari, et autres
Publié: (2025)

FDCE-Net: Underwater Image Enhancement with Embedding Frequency and Dual Color Encoder
par: Cheng, Zheng, et autres
Publié: (2024)

Learning with Geometric Priors in U-Net Variants for Polyp Segmentation
par: Vazquez, Fabian, et autres
Publié: (2026)

Learning to Adapt Foundation Model DINOv2 for Capsule Endoscopy Diagnosis
par: Zhang, Bowen, et autres
Publié: (2024)

TSMS-SAM2: Multi-scale Temporal Sampling Augmentation and Memory-Splitting Pruning for Promptable Video Object Segmentation and Tracking in Surgical Scenarios
par: Xu, Guoping, et autres
Publié: (2025)