SEER explained: Vision Models more Robust & Fair when pretrained on UNCURATED images!?

The 10 billion parameter SEER model from @MetaAI is *fairer*, even though it is trained on *uncurated* data. How so? Check out our take on this.
SPONSOR: Diffgram 👉 https://diffgram.com/

Check out our daily #MachineLearning Quiz Questions:
❓ https://www.youtube.com/c/AICoffeeBreak/community

Thanks to our Patrons who support us in Tier 2, 3, 4: 🙏
Don Rosenthal, Dres. Trost GbR, banana.dev -- Kyle Morris, Julián Salazar, Edvard Grødem, Vignesh Valliappan

Paper 📜: Goyal, Priya, Quentin Duval, Isaac Seessel, Mathilde Caron, Mannat Singh, Ishan …

explained fair images vision