As the request for deep learning solutions increases, the need for explainability is even more fundamental. In this setting, particular attention has been given to visualization techniques, that try to attribute the right relevance to each input pixel with respect to the output of the network. In this paper, we focus on Class Activation Mapping (CAM) approaches, which provide an effective visualization by taking weighted averages of the activation maps. To enhance the evaluation and the reproducibility of such approaches, we propose a novel set of metrics to quantify explanation maps, which show better effectiveness and simplify comparisons between approaches. To evaluate the appropriateness of the proposal, we compare different CAM-based visualization methods on the entire ImageNet validation set, fostering proper comparisons and reproducibility.
Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis / Poppi, Samuele; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita. - (2021), pp. 2299-2304. (Intervento presentato al convegno 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 tenutosi a Virtual nel June 19-25, 2021) [10.1109/CVPRW53098.2021.00260].
Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis
Poppi, Samuele;Cornia, Marcella
;Baraldi, Lorenzo;Cucchiara, Rita
2021
Abstract
As the request for deep learning solutions increases, the need for explainability is even more fundamental. In this setting, particular attention has been given to visualization techniques, that try to attribute the right relevance to each input pixel with respect to the output of the network. In this paper, we focus on Class Activation Mapping (CAM) approaches, which provide an effective visualization by taking weighted averages of the activation maps. To enhance the evaluation and the reproducibility of such approaches, we propose a novel set of metrics to quantify explanation maps, which show better effectiveness and simplify comparisons between approaches. To evaluate the appropriateness of the proposal, we compare different CAM-based visualization methods on the entire ImageNet validation set, fostering proper comparisons and reproducibility.File | Dimensione | Formato | |
---|---|---|---|
2021_CVPRW_Explanations.pdf
Open access
Tipologia:
AAM - Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione
2.77 MB
Formato
Adobe PDF
|
2.77 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris