PHyCLIP: $\ell_1$-Product of Hyperbolic Factors Unifies Hierarchy and Compositionality in Vision-Language Representation Learning

Documenti analoghi

• Compositional Entailment Learning for Hyperbolic Vision-Language Models
  di: Pal, Avik, et al.
  Pubblicazione: (2024)
• Learning Structured Representations with Hyperbolic Embeddings
  di: Sinha, Aditya, et al.
  Pubblicazione: (2024)
• HyperCLIP: Adapting Vision-Language models with Hypernetworks
  di: Akinwande, Victor, et al.
  Pubblicazione: (2024)
• Hierarchy-Guided Multimodal Representation Learning for Taxonomic Inference
  di: Ahmed, Sk Miraj, et al.
  Pubblicazione: (2026)
• If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions
  di: Esfandiarpoor, Reza, et al.
  Pubblicazione: (2024)