佐藤なつ | Deep Learning JP

RSA: Reducing Semantic Shift from Aggressive Augmentations for Self-supervised Learning (NeurIPS 2022)

The Forward-Forward Algorithm: Some Preliminary

ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation

Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos

GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images

Contrastive Learning as Goal-Conditioned Reinforcement Learning

Hierarchical Text-Conditional Image Generation with CLIP Latents

DayDreamer: World Models for Physical Robot Learning

Prompting Decision Transformer for Few-Shot Policy Generalization

Diffusion Model 関連研究

1 / 412 3 4 »