MoCo (2) 썸네일형 리스트형 [BYOL 논문 리뷰] - Bootstrap your own latent: A new approach to self-supervised Learning *BYOL 논문 리뷰를 코드와 같이 분석한 글입니다! SSL 입문하시는 분들께 도움이 되길 원하며 궁금한 점은 댓글로 남겨주세요. *BYOL는 Non-contrastive learning입니다. BYOL paper: https://arxiv.org/abs/2006.07733 Bootstrap your own latent: A new approach to self-supervised Learning We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and .. [MoCo 논문 리뷰] - Momentum Contrast for Unsupervised Visual Representation Learning *MoCo 논문 리뷰를 코드와 같이 분석한 글입니다! SSL 입문하시는 분들께 도움이 되길 원하며 궁금한 점은 댓글로 남겨주세요. *SSL(Self-Supervised-Learning) 중 contrastive learning을 위주로 다룹니다! Moco paper: [1911.05722] Momentum Contrast for Unsupervised Visual Representation Learning (arxiv.org) Momentum Contrast for Unsupervised Visual Representation Learning We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a.. 이전 1 다음
