Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual Path Distillation

Documenti analoghi

• Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning
  di: Zhong, Hanwen, et al.
  Pubblicazione: (2025)
• AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer
  di: Wu, Zhuguanyu, et al.
  Pubblicazione: (2024)
• CST: Calibration Side-Tuning for Parameter and Memory Efficient Transfer Learning
  di: Chen, Feng
  Pubblicazione: (2024)
• MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning
  di: Zhang, Yutong, et al.
  Pubblicazione: (2026)
• Leveraging Predicate and Triplet Learning for Scene Graph Generation
  di: Li, Jiankai, et al.
  Pubblicazione: (2024)