SIDU: Similarity Difference And Uniqueness Method for Explainable AI

Satya Mahesh Muddamsetty, Mohammad Naser Sabet Jahromi, Thomas B. Moeslund

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

66 Downloads (Pure)

Abstrakt

A new brand of technical artificial intelligence ( Explainable AI ) research has focused on trying to open up the ’black box’ and provide some explainability. This paper presents a novel visual explanation method for deep learning networks in the form of a saliency map that can effectively localize entire object regions. In contrast to the current state-of-the art methods, the proposed method shows quite promising visual explanations that can gain greater trust of human expert. Both quantitative and qualitative evaluations are carried out on both general and clinical data sets to confirm the effectiveness of the proposed method.
OriginalsprogEngelsk
Titel2020 IEEE International Conference on Image Processing (ICIP)
ForlagIEEE
Publikationsdato2020
Artikelnummer9190952
ISBN (Trykt)978-1-7281-6394-9, 978-1-7281-6396-3
ISBN (Elektronisk)978-1-7281-6395-6
DOI
StatusUdgivet - 2020
Begivenhed2020 IEEE International Conference on Image Processing (ICIP) - Abu Dhabi, United Arab Emirates
Varighed: 25 okt. 202028 okt. 2020

Konference

Konference2020 IEEE International Conference on Image Processing (ICIP)
LandUnited Arab Emirates
ByAbu Dhabi
Periode25/10/202028/10/2020
NavnIEEE International Conference on Image Processing (ICIP)
ISSN2381-8549

Fingeraftryk Dyk ned i forskningsemnerne om 'SIDU: Similarity Difference And Uniqueness Method for Explainable AI'. Sammen danner de et unikt fingeraftryk.

Citationsformater