Cover Image

FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Jiaqi, Wang, Juntuo, Sun, Zhixin, Zou, John, Balestriero, Randall
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum
by: Lu, Wenquan, et al.
Published: (2025)

Learning by Reconstruction Produces Uninformative Features For Perception
by: Balestriero, Randall, et al.
Published: (2024)

LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
by: Balestriero, Randall, et al.
Published: (2025)

On the Geometry of Deep Learning
by: Balestriero, Randall, et al.
Published: (2024)

Randomized-MLP Regularization Improves Domain Adaptation and Interpretability in DINOv2
by: Ortega, Joel Valdivia, et al.
Published: (2025)

Self-Supervised Anomaly Detection in the Wild: Favor Joint Embeddings Methods
by: Otero, Daniel, et al.
Published: (2024)

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

Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density
by: Balestriero, Randall, et al.
Published: (2025)

GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning
by: Feizi, Aarash, et al.
Published: (2024)

Deep Networks Always Grok and Here is Why
by: Humayun, Ahmed Imtiaz, et al.
Published: (2024)

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

Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning
by: Van Assel, Hugues, et al.
Published: (2025)

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

Fast Adversarial Training with Weak-to-Strong Spatial-Temporal Consistency in the Frequency Domain on Videos
by: Wang, Songping, et al.
Published: (2025)

Improving Fast Adversarial Training via Self-Knowledge Guidance
by: Jiang, Chengze, et al.
Published: (2024)

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

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

Interpreting Physics in Video World Models
by: Joseph, Sonia, et al.
Published: (2026)

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

A Lightweight Library for Energy-Based Joint-Embedding Predictive Architectures
by: Terver, Basile, et al.
Published: (2026)

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

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

UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
by: Al-Tahan, Haider, et al.
Published: (2024)

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

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

Predicting Blastocyst Formation in IVF: Integrating DINOv2 and Attention-Based LSTM on Time-Lapse Embryo Images
by: Varzaneh, Zahra Asghari, et al.
Published: (2026)

EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training
by: Wang, Yulin, et al.
Published: (2024)

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

Video-Based Performance Evaluation for ECR Drills in Synthetic Training Environments
by: Rayala, Surya, et al.
Published: (2025)

Promoting Shape Bias in CNNs: Frequency-Based and Contrastive Regularization for Corruption Robustness
by: Ranabhat, Robin Narsingh, et al.
Published: (2025)

Robustmix: Improving Robustness by Regularizing the Frequency Bias of Deep Nets
by: Ngnawe, Jonas, et al.
Published: (2023)

HP-Edit: A Human-Preference Post-Training Framework for Image Editing
by: Li, Fan, et al.
Published: (2026)

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

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

Parameter Interpolation Adversarial Training for Robust Image Classification
by: Liu, Xin, et al.
Published: (2025)

Synergistic Foundation Models for Semi-Supervised Fetal Cardiac Ultrasound Analysis: SAM-Med2D Boundary Refinement and DINOv3 Semantic Enhancement
by: Zhuang, Tonghao, et al.
Published: (2026)

D-GAP: Improving Out-of-Domain Robustness via Dataset-Agnostic and Gradient-Guided Augmentation in Frequency and Pixel Spaces
by: Wang, Ruoqi, et al.
Published: (2025)

Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition
by: Zhou, Yuxi, et al.
Published: (2026)

Reinforcement Learning-Based Prompt Template Stealing for Text-to-Image Models
by: Zou, Xiaotian
Published: (2025)

Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry
by: Fel, Thomas, et al.
Published: (2025)