Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting

Documenti analoghi

• Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models
  di: Vemulapalli, Raviteja, et al.
  Pubblicazione: (2023)
• TiC-CLIP: Continual Training of CLIP Models
  di: Garg, Saurabh, et al.
  Pubblicazione: (2023)
• MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
  di: Vasu, Pavan Kumar Anasosalu, et al.
  Pubblicazione: (2023)
• SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding
  di: Wang, Haoxiang, et al.
  Pubblicazione: (2023)
• MUSCLE: A Model Update Strategy for Compatible LLM Evolution
  di: Echterhoff, Jessica, et al.
  Pubblicazione: (2024)