Tent: Fully Test-time Adaptation by Entropy Minimization

Поделиться
HTML-код
  • Опубликовано: 3 ноя 2024

Комментарии • 7

  • @lucacazzola5327
    @lucacazzola5327 3 месяца назад

    sick channel, you're a nice orator! Working on a TTA project right now in Uni 💪

    • @soroushmehraban
      @soroushmehraban  3 месяца назад +2

      @@lucacazzola5327 Thank you so much Luca! I’ve put more recent TTA papers on my agenda to create videos about. Stay tuned🙂

    • @lucacazzola5327
      @lucacazzola5327 3 месяца назад

      @@soroushmehraban I'll definitelly check It out! Do you have by chance any paper suggestions which specifically targets improving over TPT? I'm running out of ideas (and time 😢)

    • @soroushmehraban
      @soroushmehraban  3 месяца назад

      @@lucacazzola5327 What is TPT?

    • @lucacazzola5327
      @lucacazzola5327 3 месяца назад

      ​@@soroushmehraban
      paper - "Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models"
      Basically a TTA solution which uses CLIP as backbone

    • @soroushmehraban
      @soroushmehraban  3 месяца назад

      @@lucacazzola5327 Oh sorry I didn't know about that. Thanks for introducing it though.