Skip to content

Latest commit

 

History

History
41 lines (31 loc) · 2.8 KB

[Topic]chop_object_with_different_background_to_boost_robustness.md

File metadata and controls

41 lines (31 loc) · 2.8 KB

Questions

  • 有沒有一種資料增強方法,是把該物件去背剪下,然後random抽換背景?

  • 有了這樣的方法,就能夠大幅加強物件在不同背景下被偵測出來的Precision,不會因為背景不同就找不到東西

  • google

    • data augmentation randomly substitute object
    • data augmentation with different background
  • connected papers

    • A survey on Image Data Augmentation for Deep Learning

Survey