[go: up one dir, main page]

Domain Generalization (DG) studies the capability of a deep learning model to generalize to out-of-training distributions. In the last decade, literature has been massively filled with training methodologies that claim to obtain more abstract and robust data representations to tackle domain shifts. Recent research has provided a reproducible benchmark for DG, pointing out the effectiveness of naive empirical risk minimization (ERM) over existing algorithms. Nevertheless, researchers persist in using the same outdated feature extractors, and little to no attention has been given to the effects of different backbones yet. In this paper, we go ‘‘back to the backbones’’, proposing a comprehensive analysis of their intrinsic generalization capabilities, which so far have been overlooked by the research community. We evaluate a wide variety of feature extractors, from standard residual solutions to transformer-based architectures, finding an evident linear correlation between large-scale single-domain classification accuracy and DG capability. Our extensive experimentation shows that by adopting competitive backbones in conjunction with effective data augmentation, plain ERM outperforms recent DG solutions and achieves state-of-the-art accuracy. Moreover, our additional qualitative studies reveal that novel backbones give more similar representations to same-class samples, separating different domains in the feature space. This boost in generalization capabilities leaves marginal room for DG algorithms. It suggests a new paradigm for investigating the problem, placing backbones in the spotlight and encouraging the development of consistent algorithms on top of them. The code is available at https://github.com/PIC4SeR/Back-to-Bones

Back-to-Bones: Rediscovering the role of backbones in domain generalization / Angarano, Simone; Martini, Mauro; Salvetti, Francesco; Mazzia, Vittorio; Chiaberge, Marcello. - In: PATTERN RECOGNITION. - ISSN 0031-3203. - 156:(2024), pp. 1-16. [10.1016/j.patcog.2024.110762]

Back-to-Bones: Rediscovering the role of backbones in domain generalization

Angarano, Simone;Martini, Mauro;Salvetti, Francesco;Mazzia, Vittorio;Chiaberge, Marcello
2024

Abstract

Domain Generalization (DG) studies the capability of a deep learning model to generalize to out-of-training distributions. In the last decade, literature has been massively filled with training methodologies that claim to obtain more abstract and robust data representations to tackle domain shifts. Recent research has provided a reproducible benchmark for DG, pointing out the effectiveness of naive empirical risk minimization (ERM) over existing algorithms. Nevertheless, researchers persist in using the same outdated feature extractors, and little to no attention has been given to the effects of different backbones yet. In this paper, we go ‘‘back to the backbones’’, proposing a comprehensive analysis of their intrinsic generalization capabilities, which so far have been overlooked by the research community. We evaluate a wide variety of feature extractors, from standard residual solutions to transformer-based architectures, finding an evident linear correlation between large-scale single-domain classification accuracy and DG capability. Our extensive experimentation shows that by adopting competitive backbones in conjunction with effective data augmentation, plain ERM outperforms recent DG solutions and achieves state-of-the-art accuracy. Moreover, our additional qualitative studies reveal that novel backbones give more similar representations to same-class samples, separating different domains in the feature space. This boost in generalization capabilities leaves marginal room for DG algorithms. It suggests a new paradigm for investigating the problem, placing backbones in the spotlight and encouraging the development of consistent algorithms on top of them. The code is available at https://github.com/PIC4SeR/Back-to-Bones
File in questo prodotto:
File Dimensione Formato  
b2b_new.pdf

accesso aperto

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Creative commons
Dimensione 6.37 MB
Formato Adobe PDF
6.37 MB Adobe PDF Visualizza/Apri
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/11583/2990930