Jieneng Chen
Results
3
issues of
Jieneng Chen
Hello, This is a great work and thank you. From your README I assume you do pretrain in the imageNet? How to pretrain a 3D model in a 2D image...
Add the ViTamin model, which is trained on public DataComp-1B using OpenCLIP framework and obtains 82.9% zero-shot ImageNet-1K accuracy with 436M parameters. It achieves the state-of-the-art performance on zero-shot image...
Add the ViTamin model, which is trained on public DataComp-1B using OpenCLIP framework and obtains 82.9% zero-shot ImageNet-1K accuracy with 436M parameters. This work has been accepted to CVPR 2024...