Tagged articles

DINOv2

2 articles · Page 1 of 1
HyperAI Super Neural
HyperAI Super Neural
Feb 13, 2026 · Artificial Intelligence

UCL Team Uses Federated Learning to Train Blood Morphology Models Without Sharing Data

A UCL computer‑science team presents a federated learning framework for white‑blood‑cell morphology analysis that preserves patient privacy, leverages heterogeneous clinical slide data from multiple sites, and achieves superior cross‑site performance and generalisation to unseen institutions compared with centralized training.

Blood MorphologyDINOv2ResNet-34
0 likes · 14 min read
UCL Team Uses Federated Learning to Train Blood Morphology Models Without Sharing Data
AIWalker
AIWalker
Jan 22, 2024 · Artificial Intelligence

Depth Anything: An Open-Source Large-Scale Model for Arbitrary Image Depth Estimation

Depth Anything introduces a highly practical monocular depth estimation model that leverages a 62‑million‑image unlabeled dataset, teacher‑student training, strong data perturbations, and DINOv2‑based semantic supervision to achieve zero‑shot capability and state‑of‑the‑art performance over MiDaS across multiple benchmarks.

Computer VisionDINOv2Depth Estimation
0 likes · 8 min read
Depth Anything: An Open-Source Large-Scale Model for Arbitrary Image Depth Estimation