The capability to select the relevant portion of the input is a key feature to limit the sensory input and focus on the most informative collected part. The transformer architecture is among the most performing deep neural network architectures due to the attention mechanism. The attention allows us to spot relevant connections between portions of the images and highlight these connections. Since the model is complex, it is not easy to determine which are these connections and the important areas. We discuss a technique to show these areas and highlight the regions most relevant for label attribution.
Calderaro, S., Lo Bosco, G., Rizzo, R., Vella, F. (2023). Visualization and Analysis of Transformer Attention. In A. Bruno, A. Pipitone, R. Manzotti, A. Augello, P.L. Mazzeo, F. Vella, et al. (a cura di), Proceedings of the 1st Workshop on Artificial Intelligence for Perception and Artificial Consciousness (AIxPAC 2023) co-located with the 22nd International Conference of the Italian Association for Artificial Intelligence (AIxIA 2023).
Visualization and Analysis of Transformer Attention
Calderaro, Salvatore;Lo Bosco, Giosue;Rizzo, Riccardo;Vella, Filippo
2023-01-01
Abstract
The capability to select the relevant portion of the input is a key feature to limit the sensory input and focus on the most informative collected part. The transformer architecture is among the most performing deep neural network architectures due to the attention mechanism. The attention allows us to spot relevant connections between portions of the images and highlight these connections. Since the model is complex, it is not easy to determine which are these connections and the important areas. We discuss a technique to show these areas and highlight the regions most relevant for label attribution.File | Dimensione | Formato | |
---|---|---|---|
paper_11.pdf
accesso aperto
Tipologia:
Versione Editoriale
Dimensione
7.15 MB
Formato
Adobe PDF
|
7.15 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.