Ema97

icon company Politecnico di Torino icon location Torino icon location Computer Vision, Multimodal Learning, LLMs, Diffusion Models

Results 2 issues of Ema97

Train VRC on single categories produces bad results

3 comment

Hi! I have retrained your model on another dataset (derived from ShapeNet) on single categories, (i.e. for each class I train a separate model). I found that VRC has the...

Model Selection

Hi! Thanks for you work, I wanted to ask how do you select the best model for results in the paper. Do you just take the final checkpoint at 300K...