vision-only DINOv2 backbones

Computer Vision and Pattern Recognition Machine Learning

Generalizable Visual Reinforcement Learning with Segment Anything Model

root December 29, 2023 0

This paper presents SAM-G, a new framework that uses the Segment Anything Model (SAM) to improve the generalization abilities of visual reinforcement learning (RL) agents. SAM-G uses image features from…

Computer Vision and Pattern Recognition

Detect Every Thing with Few Examples

root September 25, 2023 0

The article presents DE-ViT, a new open-set object detector that uses DINOv2 vision-only backbones. Instead of using language, DE-ViT learns new categories through example images. The authors transform multi-classification tasks…

Page 1 of 1

Press ESC to close

vision-only DINOv2 backbones

Please allow ads on our site