U tweetove putem weba ili aplikacija drugih proizvođača možete dodati podatke o lokaciji, kao što su grad ili točna lokacija. Povijest lokacija tweetova uvijek možete izbrisati. Saznajte više
Example predictions on robustness benchmarks ImageNet-A, C and P. Black texts are correct predictions made by our model and red texts are incorrect predictions by our baseline model.pic.twitter.com/eem6tlfyPX
Full comparison against state-of-the-art on ImageNet. Noisy Student is our method. Noisy Student + EfficientNet is 11% better than your favorite ResNet-50 
pic.twitter.com/BhwgJvSOYK
Method is also super simple: 1) Train a classifier on ImageNet 2) Infer labels on a much larger unlabeled dataset 3) Train a larger classifier on the combined set 4) Iterate the process, adding noise
I also highly recommend this nice video that explains the paper very well:https://www.youtube.com/watch?v=Y8YaU9mv_us …
So grateful for all the really useful work you've been releasing, Quoc - I don't know how you do it! :) I love this focus on making the most of data augmentation, pseudo-labeling, and other practically important techniques.
Thanks @jeremyphoward!
Hola please find the unroll here: Thread by @quocleix: "Want to improve accuracy and robustness of your model? Use unlabeled data! Our new work uses self-training on unlabeled […]" https://threadreaderapp.com/thread/1194334947156193280.html …
Share this if you think it's interesting. 
Worth to try this method on the whole index of Google Image Search. We did similar thing two years ago on whole Bing Image Search with some initial results reported in https://arxiv.org/abs/1708.08201 .
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.
