DeepAI AI Chat
Log In Sign Up

Active Object Manipulation Facilitates Visual Object Learning: An Egocentric Vision Study

by   Satoshi Tsutsui, et al.

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.


page 1

page 2

page 3

page 4


Self-supervisory Signals for Object Discovery and Detection

In robotic applications, we often face the challenge of discovering new ...

IterGANs: Iterative GANs to Learn and Control 3D Object Transformation

We are interested in learning visual representations which allow for 3D ...

Task-Focused Few-Shot Object Detection for Robot Manipulation

This paper addresses the problem of mobile robot manipulation of novel o...

Learning to See by Moving

The dominant paradigm for feature learning in computer vision relies on ...

Reinforcement Learning of Active Vision forManipulating Objects under Occlusions

We consider artificial agents that learn to jointly control their grippe...

Non-Parametric Self-Identification and Model Predictive Control of Dexterous In-Hand Manipulation

Building hand-object models for dexterous in-hand manipulation remains a...

A Number Sense as an Emergent Property of the Manipulating Brain

The ability to understand and manipulate numbers and quantities emerges ...