Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud

Documenti analoghi

• Learning Significant Persistent Homology Features for 3D Shape Understanding
  di: Kudeshia, Prachi, et al.
  Pubblicazione: (2026)
• A Persistent Homology Design Space for 3D Point Cloud Deep Learning
  di: Kudeshia, Prachi, et al.
  Pubblicazione: (2026)
• 3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning
  di: Hu, Naiwen, et al.
  Pubblicazione: (2024)
• CNN-JEPA: Self-Supervised Pretraining Convolutional Neural Networks Using Joint Embedding Predictive Architecture
  di: Kalapos, András, et al.
  Pubblicazione: (2024)
• JEPA for RL: Investigating Joint-Embedding Predictive Architectures for Reinforcement Learning
  di: Kenneweg, Tristan, et al.
  Pubblicazione: (2025)