-
Self-supervisory Signals for Object Discovery and Detection
In robotic applications, we often face the challenge of discovering new ...
read it
-
IterGANs: Iterative GANs to Learn and Control 3D Object Transformation
We are interested in learning visual representations which allow for 3D ...
read it
-
Learning to See by Moving
The dominant paradigm for feature learning in computer vision relies on ...
read it
-
Reinforcement Learning of Active Vision forManipulating Objects under Occlusions
We consider artificial agents that learn to jointly control their grippe...
read it
-
A Number Sense as an Emergent Property of the Manipulating Brain
The ability to understand and manipulate numbers and quantities emerges ...
read it
-
Benchmarking In-Hand Manipulation
The purpose of this benchmark is to evaluate the planning and control as...
read it
-
Contour Primitive of Interest Extraction Network Based on One-shot Learning for Object-Agnostic Vision Measurement
Image contour based vision measurement is widely applied in robot manipu...
read it
Active Object Manipulation Facilitates Visual Object Learning: An Egocentric Vision Study
Inspired by the remarkable ability of the infant visual learning system, a recent study collected first-person images from children to analyze the `training data' that they receive. We conduct a follow-up study that investigates two additional directions. First, given that infants can quickly learn to recognize a new object without much supervision (i.e. few-shot learning), we limit the number of training images. Second, we investigate how children control the supervision signals they receive during learning based on hand manipulation of objects. Our experimental results suggest that supervision with hand manipulation is better than without hands, and the trend is consistent even when a small number of images is available.
READ FULL TEXT
Comments
There are no comments yet.