"Why Do Better Loss Functions Lead to Less Transferable Features?"

Simon Kornblith et al. (2021)

> Home

Details and statistics

DOI: —

access: open

type: Conference or Workshop Paper

metadata version: 2024-08-07

- view
  - electronic edition @ neurips.cc (open access)
- export record
  dblp key:
  - conf/nips/KornblithCLN21
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/nips/KornblithCLN21
Simon Kornblith, Ting Chen, Honglak Lee, Mohammad Norouzi:
Why Do Better Loss Functions Lead to Less Transferable Features? NeurIPS 2021: 28648-28662

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.