Self-supervised video pretraining yields robust and more human-aligned visual representations

Documenti analoghi

• Intuitive physics understanding emerges from self-supervised pretraining on natural videos
  di: Garrido, Quentin, et al.
  Pubblicazione: (2025)
• Self-supervised vision-langage alignment of deep learning representations for bone X-rays analysis
  di: Englebert, Alexandre, et al.
  Pubblicazione: (2024)
• Layerwise complexity-matched learning yields an improved model of cortical area V2
  di: Parthasarathy, Nikhil, et al.
  Pubblicazione: (2023)
• Dilated Convolution with Learnable Spacings makes visual models more aligned with humans: a Grad-CAM study
  di: Chamas, Rabih, et al.
  Pubblicazione: (2024)
• The role of self-supervised pretraining in differentially private medical image analysis
  di: Arasteh, Soroosh Tayebi, et al.
  Pubblicazione: (2026)