Login / Signup
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?
Runpei Dong
Zekun Qi
Linfeng Zhang
Junbo Zhang
Jianjian Sun
Zheng Ge
Li Yi
Kaisheng Ma
Published in:
ICLR (2023)
Keyphrases
</>
learning process
perceptual information
cross modal
image representation
image retrieval
image features
image classification
learning algorithm
image data
supervised learning
multiscale
image content
learning tasks
e learning
multi modal
generative model
test images
similarity measure