Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approach

Documenti analoghi

• Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models
  di: Lu, Zhihe, et al.
  Pubblicazione: (2023)
• DreamDrone: Text-to-Image Diffusion Models are Zero-shot Perpetual View Generators
  di: Kong, Hanyang, et al.
  Pubblicazione: (2023)
• Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuning
  di: li, Bonan, et al.
  Pubblicazione: (2025)
• BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrapping
  di: Zhang, Taolin, et al.
  Pubblicazione: (2024)
• Dual-Path Adversarial Lifting for Domain Shift Correction in Online Test-time Adaptation
  di: Tang, Yushun, et al.
  Pubblicazione: (2024)