The Curious Robot: Learning Visual Representations via Physical Interactions thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

The Curious Robot: Learning Visual Representations via Physical Interactions

Published on Oct 24, 20161395 Views

What is the right supervisory signal to train visual representations? Current approaches in computer vision use category labels from datasets such as ImageNet to train ConvNets. However, in case of bi

Related categories