🐌 <span id="head1"> *Papers* </span>

• Adapter Tuning

  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)   
  • [Paper - ViT)]    
  • [Paper - Adapter)]   
  • [Paper - image-models.github.io/)]   
  • [Paper - adapters/)]   
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue) 
  • [Paper - blue)
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - adapter)]   
  • [Paper - Adapter)]   
  • [Paper - Adapter/I2V-Adapter-repo)]   
  • [Paper - blue)  
  • [Paper - cd/unet-finetune)]   
  • [Paper - VLL/CAST)]   
  • [Paper - blue)  
  • [Paper - adapter.github.io/)]   
  • [Paper
  • [Paper
  • [Paper - Tuning)]

• Prompt Tuning

  • [Paper - blue)  
  • [Paper - IDPT)]   
  • [paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)   
  • [Paper - IDPT)]   
  • [Paper - zhu/ViPT)]   
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - Visual-Prompt)]   
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - VLAA/EVP)]   
  • [Paper - Group/ILM-VP)]   
  • [Paper - blue)  
  • [Paper - blue) 
  • [Paper - prompt-learning)]   
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue) 
  • [Paper - anything)]  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - duan/DG-SCT)]   
  • [Paper - blue)  
  • [Paper - blue)  

• Prefix Tuning

  • [Paper - blue) 
  • [Paper - blue)  
  • [Paper - blue)
  • [Paper - blue) 
  • [Paper - blue) 
  • [Paper - blue)  

• Side Tuning

  • [Paper - blue) 
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue) 
  • [Paper - Side-Tuning)]   
  • [Paper - Adapter)]   
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - LST)]   
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  

• Specification Tuning

  • [Paper - blue) 
  • [Paper - Better)]
  • [Paper - blue) 
  • [Paper - blue) 
  • [Paper - blue) 
  • [Paper - pytorch)]   
  • [Paper - blue)  
  • [Paper - blue)  

• Reparameter Tuning

  • [Paper - Group/DnA)]   
  • [Paper - Group/DnA)]   
  • [Paper - Group/DnA)]   
  • [Paper - Group/DnA)]   
  • [Paper - Group/DnA)]   
  • [Paper - Group/DnA)]   
  • [Paper - Group/DnA)]   
  • [Paper - Group/DnA)]   
  • [Paper - Group/DnA)]   
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue) 
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - Chen/EFFT-EFfective-Factor-Tuning)]   
  • [Paper - blue)  
  • [Paper - ai-lab/PEViT)]   
  • [Paper - blue) 
  • [Paper - Group/DnA)]   

• Unified Tuning

  • [Paper - blue)  
  • [Paper - parameter-efficient-tuning)] 
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - blue)  
  • [Paper - PETL)]   

<p align=center>𝓐𝔀𝓮𝓼𝓸𝓶𝓮 𝓟𝓪𝓻𝓪𝓶𝓮𝓽𝓮𝓻-𝓔𝓯𝓯𝓲𝓬𝓲𝓮𝓷𝓽 𝓣𝓻𝓪𝓷𝓼𝓯𝓮𝓻 𝓛𝓮𝓪𝓻𝓷𝓲𝓷𝓰</p>

• GitHub forks
• GitHub activity
• GitHub issues
• ![Awesome
• ![Maintenance - activity)
• GitHub stars

💬 <span id="head1"> *Keywords* </span>

🎯 <span id="head1"> *Datasets of Visual PETL* </span>

• Unified Tuning

  • Visual prompt tuning - Grained Visual Classification tasks. |
  • A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark - 1k consists of 19 diverse visual classification tasks.|
  • The kinetics human action video dataset. - OA3Y50OWtPJ/view?usp=sharing) | Video Action Recognition|
  • The “something something” Video Database for Learning and Evaluating Visual Common Sense - datasets/something-something) | Video Action Recognition|
  • HMDB:ALargeVideo Database for Human Motion Recognition - lab.clps.brown.edu/resource/hmdb-a-large-human-motion-database/) | Video Action Recognition|
  • RESOUND: Towards Action Recognition without Representation Bias
  • UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
  • Microsoft COCO: Common Objects in Context
  • Semantic Understanding of Scenes through the ADE20K Dataset
  • The Pascal Visual Object Classes Challenge: A Retrospective