论文4问O

文章目录

  • Exploring Plain Vision Transformer Backbones for Object Detection(ViTDet)
    • Method
      • 提出了简单特征金字塔(SFP)网络
      • Backbone adaptation主干适应(跨窗口信息传递)
    • conclusion
  • Masked Autoencoders Are Scalable Vision Learners
    • Method(关键)
      • Masking
      • MAE encoder
      • MAE decoder
      • Reconstruction target
      • Simple implementation
      • <

你可能感兴趣的:(论文反馈,人工智能,深度学习)