DAIT: Distillation from Vision-Language Models to Lightweight Classifiers with Adaptive Intermediate Teacher Transfer

Documenti analoghi

• Revisiting Cross-Architecture Distillation: Adaptive Dual-Teacher Transfer for Lightweight Video Models
  di: Peng, Ying, et al.
  Pubblicazione: (2025)
• AMMKD: Adaptive Multimodal Multi-teacher Distillation for Lightweight Vision-Language Models
  di: Li, Yuqi, et al.
  Pubblicazione: (2025)
• Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models
  di: Yu, Yu-Chu, et al.
  Pubblicazione: (2024)
• Visual-Advantage On-Policy Distillation for Vision-Language Models
  di: Liu, Ruiqi, et al.
  Pubblicazione: (2026)
• MMT-ARD: Multimodal Multi-Teacher Adversarial Distillation for Robust Vision-Language Models
  di: Li, Yuqi, et al.
  Pubblicazione: (2025)