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.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
non disponibili
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.
https://hdl.handle.net/11583/2971539