官方服务：
资源简介：
Offline DINOv2 weights (small + base) for knee training
面向膝关节训练的离线DINOv2权重（小型版与基础版）
应用场景：
创建时间：
2026-08-10
相关数据集
FOMO-MRI/FOMO260K
FOMO260K是一个大规模的大脑MRI扫描数据集，包括临床和研究级扫描，涵盖了多种序列，如T1、MPRAGE、T2、T2*、FLAIR、SWI、T1c、PD、DWI、ADC等。数据集包含55,378名受试者、77,589次会话和260,927次扫描。该数据集是OpenMind和FOMO45K的超集。数据以NIfTI文件格式提供，并遵循略微修改的BIDS格式。数据集还包括参与者信息、文件映射和MR
Hugging Face2026-05-06 更新80
PASS: An ImageNet replacement for self-supervised pretraining without humans
Computer vision has long relied on ImageNet and other large datasets of images sampled from the Internet for pretraining models. However, these datasets have ethical and technical shortcomings, such a
NIAID Data Ecosystem50
CPIA Dataset_Part06: A Comprehensive Pathological Image Analysis Dataset for Self-supervised Learning Pre-training
Pathological image analysis is a crucial field in computer-aided diagnosis. Transfer learning using models initialized on natural images has improved the downstream pathological performance. However,
科学数据银行2024-04-16 更新40
falafel-hockey/sentinel2-lejepa-global-diverse-256
--- language: - en license: cc-by-sa-4.0 pretty_name: Sentinel-2 LeJEPA Preset-Biased (Small) tags: - earth-observation - sentinel-2 - self-supervised-learning - satellite-imagery - pretraining - remo
Hugging Face2026-04-05 更新50
Unlabeled Sentinel 2 time series dataset (validation): Self-supervised Spatio-Temporal Representation Learning of Satellite Image Time Series
This is a part of the unlabeled Sentinel 2 (S2) L2A dataset composed of patch time series acquired over France used to pretrain U-BARN. For further details, see section IV.A of the pre-print article "
NIAID Data Ecosystem40
