Deep neural networks achieve outstanding results in a large variety of tasks, often outperforming human experts. However, a known limitation of current neural architectures is the poor accessibility to understand and interpret the network response to a given input. This is directly related to the huge number of variables and the associated non-linearities of neural models, which are often used as black boxes. When it comes to critical applications as autonomous driving, security and safety, medicine and health, the lack of interpretability of the network behavior tends to induce skepticism and limited trustworthiness, despite the accurate performance of such systems in the given task. Furthermore, a single metric, such as the classification accuracy, provides a non-exhaustive evaluation of most realworld scenarios. In this paper, we want to make a step forward towards interpretability in neural networks, providing new tools to interpret their behavior. We present Agglomerator, a framework capable of providing a representation of part-whole hierarchies from visual cues and organizing the input distribution matching the conceptual-semantic hierarchical structure between classes. We evaluate our method on common datasets, such as SmallNORB, MNIST, FashionMNIST, CIFAR-10, and CIFAR-100, providing a more interpretable model than other state-of-the-art approaches.

Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks / Garau, N.; Bisagno, N.; Sambugaro, Z.; Conci, N.. - (2022), pp. 13679-13688. (Intervento presentato al convegno 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 tenutosi a New Orleans, LA, USA nel 18-24 June 2022) [10.1109/CVPR52688.2022.01332].

Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks

Garau N.;Bisagno N.;Sambugaro Z.;Conci N.
2022-01-01

Abstract

Deep neural networks achieve outstanding results in a large variety of tasks, often outperforming human experts. However, a known limitation of current neural architectures is the poor accessibility to understand and interpret the network response to a given input. This is directly related to the huge number of variables and the associated non-linearities of neural models, which are often used as black boxes. When it comes to critical applications as autonomous driving, security and safety, medicine and health, the lack of interpretability of the network behavior tends to induce skepticism and limited trustworthiness, despite the accurate performance of such systems in the given task. Furthermore, a single metric, such as the classification accuracy, provides a non-exhaustive evaluation of most realworld scenarios. In this paper, we want to make a step forward towards interpretability in neural networks, providing new tools to interpret their behavior. We present Agglomerator, a framework capable of providing a representation of part-whole hierarchies from visual cues and organizing the input distribution matching the conceptual-semantic hierarchical structure between classes. We evaluate our method on common datasets, such as SmallNORB, MNIST, FashionMNIST, CIFAR-10, and CIFAR-100, providing a more interpretable model than other state-of-the-art approaches.
2022
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA
IEEE Computer Society
978-1-6654-6946-3
Garau, N.; Bisagno, N.; Sambugaro, Z.; Conci, N.
Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks / Garau, N.; Bisagno, N.; Sambugaro, Z.; Conci, N.. - (2022), pp. 13679-13688. (Intervento presentato al convegno 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 tenutosi a New Orleans, LA, USA nel 18-24 June 2022) [10.1109/CVPR52688.2022.01332].
File in questo prodotto:
File Dimensione Formato  
Garau_Interpretable_Part-Whole_Hierarchies_and_Conceptual-Semantic_Relationships_in_Neural_Networks_CVPR_2022_paper.pdf

accesso aperto

Descrizione: CVPR version
Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 2.87 MB
Formato Adobe PDF
2.87 MB Adobe PDF Visualizza/Apri
Interpretable_part-whole_hierarchies_and_conceptual-semantic_relationships_in_neural_networks.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 2.66 MB
Formato Adobe PDF
2.66 MB Adobe PDF   Visualizza/Apri

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/11572/379269
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 8
  • ???jsp.display-item.citation.isi??? 6
social impact