JieShibo / PETL-ViT

[ICCV 2023] Binary Adapters, [AAAI 2023] FacT, [Tech report] Convpass

Parameter-Efficient Transfer Learning on Vision Transformers

Some exploration of Parameter-Efficient Transfer Learning in vision.

• Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy

  • [ICCV 2023]

• FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer

  • [AAAI 2023 Oral]

• Convolutional Bypasses Are Better Vision Transformer Adapters

  • [Tech Report 2022]