A Sensorimotor Perspective on Grounding the Semantic of Simple Visual Features

05/11/2018
by   Alban Laflaquière, et al.
0

In Machine Learning and Robotics, the semantic content of visual features is usually provided to the system by a human who interprets its content. On the contrary, strictly unsupervised approaches have difficulties relating the statistics of sensory inputs to their semantic content without also relying on prior knowledge introduced in the system. We proposed in this paper to tackle this problem from a sensorimotor perspective. In line with the Sensorimotor Contingencies Theory, we make the fundamental assumption that the semantic content of sensory inputs at least partially stems from the way an agent can actively transform it. We illustrate our approach by formalizing how simple visual features can induce invariants in a naive agent's sensorimotor experience, and evaluate it on a simple simulated visual system. Without any a priori knowledge about the way its sensorimotor information is encoded, we show how an agent can characterize the uniformity and edge-ness of the visual features it interacts with.

READ FULL TEXT

page 4

page 5

research
10/03/2018

Grounding the Experience of a Visual Field through Sensorimotor Contingencies

Artificial perception is traditionally handled by hand-designing task sp...
research
08/03/2016

Autonomous Grounding of Visual Field Experience through Sensorimotor Prediction

In a developmental framework, autonomous robots need to explore the worl...
research
06/19/2017

Exploring Content-based Artwork Recommendation with Metadata and Visual Features

Compared to other areas, artwork recommendation has received little atte...
research
07/24/2019

Learning abstract perceptual notions: the example of space

Humans are extremely swift learners. We are able to grasp highly abstrac...
research
02/26/2021

Class Knowledge Overlay to Visual Feature Learning for Zero-Shot Image Classification

New categories can be discovered by transforming semantic features into ...
research
10/02/2018

Unsupervised Emergence of Spatial Structure from Sensorimotor Prediction

Despite its omnipresence in robotics application, the nature of spatial ...
research
06/04/2019

Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor Prediction

Despite its omnipresence in robotics application, the nature of spatial ...

Please sign up or login with your details

Forgot password? Click here to reset