PREDICTING SALIENCY MAPS FOR ASD PEOPLE - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2019

PREDICTING SALIENCY MAPS FOR ASD PEOPLE

Abstract

This paper presents a novel saliency prediction model for children with autism spectrum disorder (ASD). We design a new convolution neural network and train it with a new ASD dataset. Among the contributions , we can cite the coarse-to-fine architecture as well as the loss function which embeds a regularization term. We also discuss about some data augmentation methods for ASD dataset. Experimental results show that the proposed model performs better than 6 models, one supervised model finetuned with the ASD dataset. Contrary to control people, our results hint that no center bias apply in visuall attention for autistic children.
Fichier principal
Vignette du fichier
ASD_ICME2019(2).pdf (5.31 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02264907 , version 1 (07-08-2019)

Identifiers

  • HAL Id : hal-02264907 , version 1

Cite

Alexis Nebout, Weijie Wei, Zhi Liu, Lijin Huang, Olivier Le Meur. PREDICTING SALIENCY MAPS FOR ASD PEOPLE. ICME Workshop, Jul 2019, Shanghai, China. ⟨hal-02264907⟩
76 View
228 Download

Share

Gmail Facebook X LinkedIn More