Deciphering the Role of Representation Disentanglement: Investigating Compositional Generalization in CLIP Models

Documenti analoghi

• Language Plays a Pivotal Role in the Object-Attribute Compositional Generalization of CLIP
  di: Abbasi, Reza, et al.
  Pubblicazione: (2024)
• CLIP Under the Microscope: A Fine-Grained Analysis of Multi-Object Representation
  di: Abbasi, Reza, et al.
  Pubblicazione: (2025)
• Analyzing CLIP's Performance Limitations in Multi-Object Scenarios: A Controlled High-Resolution Study
  di: Abbasi, Reza, et al.
  Pubblicazione: (2025)
• Diffusion Beats Autoregressive: An Evaluation of Compositional Generation in Text-to-Image Models
  di: Marioriyad, Arash, et al.
  Pubblicazione: (2024)
• Attention Overlap Is Responsible for The Entity Missing Problem in Text-to-image Diffusion Models!
  di: Marioriyad, Arash, et al.
  Pubblicazione: (2024)