Upsampling DINOv2 features for unsupervised vision tasks and weakly supervised materials segmentation

Documenti analoghi

• Maybe you don't need a U-Net: convolutional feature upsampling for materials micrograph segmentation
  di: Docherty, Ronan, et al.
  Pubblicazione: (2025)
• Benchmarking foundation models as feature extractors for weakly-supervised computational pathology
  di: Neidlinger, Peter, et al.
  Pubblicazione: (2024)
• Extending 2D foundational DINOv3 representations to 3D segmentation of neonatal brain MR images
  di: Usman, Annayah, et al.
  Pubblicazione: (2026)
• Phase-fraction guided denoising diffusion model for augmenting multiphase steel microstructure segmentation via micrograph image-mask pair synthesis
  di: Nguyen, Hoang Hai Nam, et al.
  Pubblicazione: (2025)
• Assessing the Performance of the DINOv2 Self-supervised Learning Vision Transformer Model for the Segmentation of the Left Atrium from MRI Images
  di: Kundu, Bipasha, et al.
  Pubblicazione: (2024)