Skip to content

Instantly share code, notes, and snippets.

@harshraj22

harshraj22/IdeaList.md

Last active August 13, 2021 11:16
Show Gist options
  • Save harshraj22/cc64a15c658f964f588ff5c13bacbcde to your computer and use it in GitHub Desktop.
Save harshraj22/cc64a15c658f964f588ff5c13bacbcde to your computer and use it in GitHub Desktop.
Download ZIP
New ideas for BTP: Visual Question Answering
Raw
IdeaList.md
  • 1x1 convolutions have been extensively used to reduce the number of parameters without affecting the results much
  • Deep Mutual Learning: Unlike bagging/ boosting, models learn jointly, and help each other to fit well
  • Skip connections: Help solving degradation problem without adding parameters.
  • Hard Sample Mining
@harshraj22
Copy link
Author

Knowledge distillation for building small models (small num of parameters) with high performance.

@harshraj22
Copy link
Author

Discussion moved to vqa/wiki

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment