Few-shot
このタグの解説について
この解説文は、すでに終了したサービス「はてなキーワード」内で有志のユーザーが作成・編集した内容に基づいています。その正確性や網羅性をはてなが保証するものではありません。問題のある記述を発見した場合には、お問い合わせフォームよりご連絡ください。関連ブログ
ネットで話題
もっと見る
logmi.jp
github.com
www.kikagaku.co.jp15ブックマークLanguage Models are Few-Shot LearnersRecent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task. While typically task-agnostic in architecture, this method still requires task-specific fine-tuning datasets of thousands or tens o...
arxiv.org
arxiv.org
github.com
zenn.dev8ブックマークFew-Shot Adversarial Learning of Realistic Neural Talking Head ModelsSeveral recent works have shown how highly realistic human head images can be obtained by training convolutional neural networks to generate them. In order to create a personalized talking head model, these works require training on a large dataset of images of a single person. However, in many p...
arxiv.org
arxiv.org
atmarkit.itmedia.co.jp
xtech.nikkei.com
