Deep Affordance-grounded Sensorimotor Object Recognition

04/10/2017
by   Spyridon Thermos, et al.
0

It is well-established by cognitive neuroscience that human perception of objects constitutes a complex process, where object appearance information is combined with evidence about the so-called object "affordances", namely the types of actions that humans typically perform when interacting with them. This fact has recently motivated the "sensorimotor" approach to the challenging task of automatic object recognition, where both information sources are fused to improve robustness. In this work, the aforementioned paradigm is adopted, surpassing current limitations of sensorimotor object recognition research. Specifically, the deep learning paradigm is introduced to the problem for the first time, developing a number of novel neuro-biologically and neuro-physiologically inspired architectures that utilize state-of-the-art neural networks for fusing the available information sources in multiple ways. The proposed methods are evaluated using a large RGB-D corpus, which is specifically collected for the task of sensorimotor object recognition and is made publicly available. Experimental results demonstrate the utility of affordance information to object recognition, achieving an up to 29 error reduction by its inclusion.

READ FULL TEXT

page 3

page 5

page 6

page 8

research
03/06/2018

Learning Scene Gist with Convolutional Neural Networks to Improve Object Recognition

Advancements in convolutional neural networks (CNNs) have made significa...
research
07/29/2016

SwiDeN : Convolutional Neural Networks For Depiction Invariant Object Recognition

Current state of the art object recognition architectures achieve impres...
research
12/11/2019

Object Recognition with Human in the Loop Intelligent Frameworks

Classifiers embedded within human in the loop visual object recognition ...
research
04/12/2016

Orientation-boosted Voxel Nets for 3D Object Recognition

Recent work has shown good recognition results in 3D object recognition ...
research
01/30/2015

Hyper-parameter optimization of Deep Convolutional Networks for object recognition

Recently sequential model based optimization (SMBO) has emerged as a pro...
research
02/15/2021

Seeing by haptic glance: reinforcement learning-based 3D object Recognition

Human is able to conduct 3D recognition by a limited number of haptic co...
research
06/19/2023

Object Topological Character Acquisition by Inductive Learning

Understanding the shape and structure of objects is undoubtedly extremel...

Please sign up or login with your details

Forgot password? Click here to reset