Tweeted By @lmthang

What's the difference between recent works in semi-supervised learning? Key: consistency training (UDA, FixMatch, ReMixMatch, ICT, etc.) and self-training (#NoisyStudent), see photo below and my recent talk (https://t.co/DBTQH2xHHL with bonus slides on #MeenaBot!). pic.twitter.com/R7vXmrfjiq

— Thang Luong (@lmthang) March 4, 2020