Copertina

Randomized-MLP Regularization Improves Domain Adaptation and Interpretability in DINOv2

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ortega, Joel Valdivia, Lamm, Lorenz, Eckardt, Franziska, Schworm, Benedikt, Jasnin, Marion, Peng, Tingying
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Vision Transformer-Conditioned UNet for Domain-Adaptive Semantic Segmentation
di: Ortega, Joel Valdivia, et al.
Pubblicazione: (2026)

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

MM-UNet: A Mixed MLP Architecture for Improved Ophthalmic Image Segmentation
di: Xiao, Zunjie, et al.
Pubblicazione: (2024)

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

FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed
di: Zhang, Jiaqi, et al.
Pubblicazione: (2025)

Graph Residual Noise Learner Network for Brain Connectivity Graph Prediction
di: Demirbilek, Oytun, et al.
Pubblicazione: (2024)

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

General Purpose Image Encoder DINOv2 for Medical Image Registration
di: Song, Xinrui, et al.
Pubblicazione: (2024)

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

Evaluating General Purpose Vision Foundation Models for Medical Image Analysis: An Experimental Study of DINOv2 on Radiology Benchmarks
di: Baharoon, Mohammed, et al.
Pubblicazione: (2023)

DINOv3 as a Frozen Encoder for CRPS-Oriented Probabilistic Rainfall Nowcasting
di: Filho, Luciano Araujo Dourado, et al.
Pubblicazione: (2025)

Training Transitive and Commutative Multimodal Transformers with LoReTTa
di: Tran, Manuel, et al.
Pubblicazione: (2023)

Medical Slice Transformer: Improved Diagnosis and Explainability on 3D Medical Images with DINOv2
di: Müller-Franzes, Gustav, et al.
Pubblicazione: (2024)

Training Frozen Feature Pyramid DINOv2 for Eyelid Measurements with Infinite Encoding and Orthogonal Regularization
di: Chen, Chun-Hung
Pubblicazione: (2025)

GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation
di: Li, Wenhao, et al.
Pubblicazione: (2022)

Revealing the Semantic Selection Gap in DINOv3 through Training-Free Few-Shot Segmentation
di: Zakir, Hussni Mohd, et al.
Pubblicazione: (2026)

Group Orthogonalization Regularization For Vision Models Adaptation and Robustness
di: Kurtz, Yoav, et al.
Pubblicazione: (2023)

See Through the Noise: Improving Domain Generalization in Gaze Estimation
di: Peng, Yanming, et al.
Pubblicazione: (2026)

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

DINOv2 Rocks Geological Image Analysis: Classification, Segmentation, and Interpretability
di: Brondolo, Florent, et al.
Pubblicazione: (2024)

Low-resource finetuning of foundation models beats state-of-the-art in histopathology
di: Roth, Benedikt, et al.
Pubblicazione: (2024)

Lightweight Data-Free Denoising for Detail-Preserving Biomedical Image Restoration
di: Chobola, Tomáš, et al.
Pubblicazione: (2025)

Regularizing Subspace Redundancy of Low-Rank Adaptation
di: Zhu, Yue, et al.
Pubblicazione: (2025)

Open-Set Domain Adaptation for Semantic Segmentation
di: Choe, Seun-An, et al.
Pubblicazione: (2024)

An Example for Domain Adaptation Using CycleGAN
di: Zhao, Yanhua
Pubblicazione: (2026)

Rethinking Unsupervised Domain Adaptation for Semantic Segmentation
di: Wang, Zhijie, et al.
Pubblicazione: (2022)

Domain Adaptation of VLM for Soccer Video Understanding
di: Jiang, Tiancheng, et al.
Pubblicazione: (2025)

Temporal vs. Spatial: Comparing DINOv3 and V-JEPA2 Feature Representations for Video Action Analysis
di: Kodathala, Sai Varun, et al.
Pubblicazione: (2025)

Lightweight Distillation of SAM 3 and DINOv3 for Edge-Deployable Individual-Level Livestock Monitoring and Longitudinal Visual Analytics
di: Yang, Haiyu, et al.
Pubblicazione: (2026)

Addressing Domain Shift via Imbalance-Aware Domain Adaptation in Embryo Development Assessment
di: Li, Lei, et al.
Pubblicazione: (2025)

Domain Adaptation for Image Classification of Defects in Semiconductor Manufacturing
di: Poniatowski, Adrian, et al.
Pubblicazione: (2025)

Unsupervised Federated Domain Adaptation for Segmentation of MRI Images
di: Nananukul, Navapat, et al.
Pubblicazione: (2024)

Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment
di: Zhao, Yaze, et al.
Pubblicazione: (2026)

Resolution scaling governs DINOv3 transfer performance in chest radiograph classification
di: Arasteh, Soroosh Tayebi, et al.
Pubblicazione: (2025)

Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection
di: Zhang, Zhanwei, et al.
Pubblicazione: (2024)

DINOv3
di: Siméoni, Oriane, et al.
Pubblicazione: (2025)

Transcending Domains through Text-to-Image Diffusion: A Source-Free Approach to Domain Adaptation
di: Chopra, Shivang, et al.
Pubblicazione: (2023)

AdaEmbed: Semi-supervised Domain Adaptation in the Embedding Space
di: Mottaghi, Ali, et al.
Pubblicazione: (2024)

Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation
di: Yu, Xiaowei, et al.
Pubblicazione: (2024)

SWAT: Sliding Window Adversarial Training for Gradual Domain Adaptation
di: Wang, Zixi, et al.
Pubblicazione: (2025)