DeepAI
Log In Sign Up

Self-Calibrating Active Binocular Vision via Active Efficient Coding with Deep Autoencoders

01/27/2021
by   Charles Wilmot, et al.
0

We present a model of the self-calibration of active binocular vision comprising the simultaneous learning of visual representations, vergence, and pursuit eye movements. The model follows the principle of Active Efficient Coding (AEC), a recent extension of the classic Efficient Coding Hypothesis to active perception. In contrast to previous AEC models, the present model uses deep autoencoders to learn sensory representations. We also propose a new formulation of the intrinsic motivation signal that guides the learning of behavior. We demonstrate the performance of the model in simulations.

READ FULL TEXT
06/21/2016

An active efficient coding model of the optokinetic nystagmus

Optokinetic nystagmus (OKN) is an involuntary eye movement responsible f...
03/15/2020

Active Perception and Representation for Robotic Manipulation

The vast majority of visual animals actively control their eyes, heads, ...
12/31/2018

Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Active Tasks

One of the ultimate promises of computer vision is to help robotic agent...
01/24/2021

Exploitation of Image Statistics with Sparse Coding in the Case of Stereo Vision

The sparse coding algorithm has served as a model for early processing i...
12/02/2021

SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency

In this paper, we explore how we can build upon the data and models of I...