Despite the popularity that saliency models have gained in the computer vision community, they are most often conceived, exploited and benchmarked without taking heed of a number of problems and subtle issues they bring about. When saliency maps are used as proxies for the likelihood of fixating a location in a viewed scene, one such issue is the temporal dimension of visual attention deployment. Through a simple simulation it is shown how neglecting this dimension leads to results that at best cast shadows on the predictive performance of a model and its assessment via benchmarking procedures.

Problems with Saliency Maps / G. Boccignone, V. Cuculo, A. D’Amelio (LECTURE NOTES IN ARTIFICIAL INTELLIGENCE). - In: Image Analysis and Processing – ICIAP 2019 / [a cura di] E. Ricci, S. Rota Bulo', C. Snoek, O.Lanz, S. Messelodi, N. Sebe. - Prima edizione. - [s.l] : Springer Nature, 2019 Sep. - ISBN 9783030306441. - pp. 35-46 (( Intervento presentato al 20. convegno International Conference on Image Analysis and Processing – ICIAP 2019 tenutosi a Trento nel 2019 [10.1007/978-3-030-30645-8_4].

Problems with Saliency Maps

G. Boccignone;V. Cuculo
;
A. D’Amelio
2019-09

Abstract

Despite the popularity that saliency models have gained in the computer vision community, they are most often conceived, exploited and benchmarked without taking heed of a number of problems and subtle issues they bring about. When saliency maps are used as proxies for the likelihood of fixating a location in a viewed scene, one such issue is the temporal dimension of visual attention deployment. Through a simple simulation it is shown how neglecting this dimension leads to results that at best cast shadows on the predictive performance of a model and its assessment via benchmarking procedures.
Saliency model; Visual attention; Gaze deployment
Settore ING-INF/05 - Sistemi di Elaborazione delle Informazioni
Settore INF/01 - Informatica
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
2019_ICIAP.pdf

accesso aperto

Tipologia: Pre-print (manoscritto inviato all'editore)
Dimensione 895.81 kB
Formato Adobe PDF
895.81 kB Adobe PDF Visualizza/Apri
Boccignone2019_Chapter_ProblemsWithSaliencyMaps.pdf

accesso riservato

Tipologia: Publisher's version/PDF
Dimensione 773.79 kB
Formato Adobe PDF
773.79 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/2434/675241
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 0
social impact