upura https://blog.hatena.ne.jp/upura/ u++の備忘録 https://upura.hatenablog.com/ 論文メモ Kaggle 画像処理 twitterで流れてきたGoogleの論文が、最近のKaggleでも頻繁に使われる「Pseudo Labeling」を拡張した興味深いものでした。本記事では、簡単にこの論文を紹介します。 Last week we released the checkpoints for SOTA ImageNet models trained by NoisyStudent. Due to popular demand, we’ve also opensourced an implementation of NoisyStudent. The code uses SVHN for demonstration… 190 <iframe src="https://hatenablog-parts.com/embed?url=https%3A%2F%2Fupura.hatenablog.com%2Fentry%2F2020%2F02%2F18%2F180500" title="【論文メモ】Self-training with Noisy Student improves ImageNet classification - u++の備忘録" class="embed-card embed-blogcard" scrolling="no" frameborder="0" style="display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;"></iframe> https://cdn-ak.f.st-hatena.com/images/fotolife/u/upura/20200218/20200218124212.png Hatena Blog https://hatena.blog 2020-02-18 18:05:00 rich https://upura.hatenablog.com/entry/2020/02/18/180500 1.0 100%