Learning More by Seeing Less: Structure First Learning for Efficient, Transferable, and Human-Aligned Vision

Documenti analoghi

• Does resistance to style-transfer equal Global Shape Bias? Measuring network sensitivity to global shape configuration
  di: Wen, Ziqi, et al.
  Pubblicazione: (2023)
• Perceptual Inductive Bias Is What You Need Before Contrastive Learning
  di: Li, Tianqin, et al.
  Pubblicazione: (2025)
• From Local Cues to Global Percepts: Emergent Gestalt Organization in Self-Supervised Vision Models
  di: Li, Tianqin, et al.
  Pubblicazione: (2025)
• Seeing More with Less: Video Capsule Endoscopy with Multi-Task Learning
  di: Werner, Julia, et al.
  Pubblicazione: (2025)
• See More, Store Less: Memory-Efficient Resolution for Video Moment Retrieval
  di: Jeon, Mingyu, et al.
  Pubblicazione: (2026)