Recent developments have resulted in multiple techniques trying to explain how deep neural networks achieve their predictions. The explainability maps provided by such techniques are useful to understand what the network has learned and increase user confidence in critical applications such as the medical field or autonomous driving. Nonetheless, they typically have very low resolutions, severely limiting their capability of identifying finer details or multiple subjects. In this paper we employ an encoder-decoder architecture with skip connection known as U-Net, originally developed for segmenting medical images, as an image classifier and we show that state of the art explainable techniques applied to U-Net can generate pixel level explanation maps for images of any resolution.

High Resolution Explanation Maps for CNNs using Segmentation Networks / Mascolini, Alessio; Ponzio, Francesco; Macii, Enrico; Ficarra, Elisa; Di Cataldo, Santa. - (2022), pp. 1-3. (Intervento presentato al convegno 2022 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) tenutosi a Rome (Italy) nel 12-16 September 2022) [10.1109/VL/HCC53370.2022.9833004].

High Resolution Explanation Maps for CNNs using Segmentation Networks

Mascolini, Alessio;Ponzio, Francesco;Macii, Enrico;Di Cataldo, Santa
2022

Abstract

Recent developments have resulted in multiple techniques trying to explain how deep neural networks achieve their predictions. The explainability maps provided by such techniques are useful to understand what the network has learned and increase user confidence in critical applications such as the medical field or autonomous driving. Nonetheless, they typically have very low resolutions, severely limiting their capability of identifying finer details or multiple subjects. In this paper we employ an encoder-decoder architecture with skip connection known as U-Net, originally developed for segmenting medical images, as an image classifier and we show that state of the art explainable techniques applied to U-Net can generate pixel level explanation maps for images of any resolution.
2022
978-1-6654-4214-5
File in questo prodotto:
File Dimensione Formato  
VLHCC_2022_Camera_Ready (3).pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Pubblico - Tutti i diritti riservati
Dimensione 992.65 kB
Formato Adobe PDF
992.65 kB Adobe PDF Visualizza/Apri
High_Resolution_Explanation_Maps_for_CNNs_using_Segmentation_Networks.pdf

accesso riservato

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.68 MB
Formato Adobe PDF
1.68 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
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: https://hdl.handle.net/11583/2971539