Tweeted By @ml_review
Revisiting Self-Supervised Visual Representation Learning
— ML Review (@ml_review) February 3, 2019
By @__kolesnikov__ @XiaohuaZhai @giffmana
Investigates how architecture design influences representation quality
New SoTA for visual representation learned without labelshttps://t.co/y5USX7chILhttps://t.co/uCeG0s9l3z pic.twitter.com/sFRKltYKok