On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline

Add code
Dec 12, 2022
Nicklas Hansen, Zhecheng Yuan, Yanjie Ze, Tongzhou Mu, Aravind Rajeswaran, Hao Su, Huazhe Xu, Xiaolong Wang
Figure 1 for On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline
Figure 2 for On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline
Figure 3 for On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline
Figure 4 for On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

We revisit a simple Learning-from-Scratch baseline for visuo-motor control that uses data augmentation and a shallow ConvNet. We find that this baseline has competitive performance with recent methods that leverage frozen visual representations trained on large-scale vision datasets.

* to pre-train; not to pre-train  
View paper onarxiv iconopen_review iconOpenReview

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon