dinov2

Tag

Cards List
#dinov2

FedCC: A Low-Resource Federated Adaptation of Foundation Models for Robust Corpus Callosum localization in Fetal Ultrasound Images

arXiv cs.LG · 2026-07-22 Cached

FedCC proposes a federated learning framework combining a frozen DINOv2 backbone with a lightweight YOLO detection head and LoRA modules for robust corpus callosum localization in fetal ultrasound images, achieving strong performance with greatly reduced communication cost in a multi-center setting.

0 favorites 0 likes
#dinov2

RiT: Vanilla Diffusion Transformers Suffice in Representation Space

Hugging Face Daily Papers · 2026-05-21 Cached

The paper introduces RiT, a vanilla Diffusion Transformer trained on frozen DINOv2 features using flow matching with x-prediction, achieving competitive FID scores on ImageNet 256×256 with fewer parameters and fast sampling without distillation.

0 favorites 0 likes
#dinov2

MARCO: Navigating the Unseen Space of Semantic Correspondence

Hugging Face Daily Papers · 2026-04-20 Cached

MARCO introduces a compact, fast model for semantic correspondence that achieves state-of-the-art accuracy and generalization to unseen keypoints using a coarse-to-fine objective and self-distillation framework with DINOv2.

0 favorites 0 likes
← Back to home

Submit Feedback