Awesome Self-Supervised Learning / 计算机视觉

BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation

作者：Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi, Noboru Harada, Kunio Kashino · 来源：arXiv preprint · 类别：音频 · 发布日期：2021-03-11

自监督学习表征学习图像表征几何学习音频
新标签打开 AlphaXiv新标签打开 Code
BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation figure
AlphaXiv 中文概览（可滚动查看）