Within modern Deep Learning setups, data augmentation is the weapon of choice when dealing with narrow datasets or with a poor range of different samples. However, the benefits of data augmentation are abysmal when applied to a dataset which is inherently unable to cover all the categories to be classified with a significant number of samples. To deal with such desperate scenarios, we propose a possible last resort: Cross-Dataset Data Augmentation. That is, the creation of new samples by morphing observations from a different source into credible specimens for the training dataset. Of course specific and strict conditions must be satisfied for this trick to work. In this paper we propose a general set of strategies and rules for Cross-Dataset Data Augmentation and we demonstrate its feasibility over a concrete case study. Even without defining any new formal approach, we think that the preliminary results of our paper are worth to produce a broader discussion on this topic.

Cross-Dataset Data Augmentation for Convolutional Neural Networks Training

Gasparetto, Andrea
;
Ressi, Dalila;Bergamasco, Filippo;Pistellato, Mara;Cosmo, Luca;BOSCHETTI, MARCO;URSELLA, Enrico;Albarelli, Andrea
2018-01-01

Abstract

Within modern Deep Learning setups, data augmentation is the weapon of choice when dealing with narrow datasets or with a poor range of different samples. However, the benefits of data augmentation are abysmal when applied to a dataset which is inherently unable to cover all the categories to be classified with a significant number of samples. To deal with such desperate scenarios, we propose a possible last resort: Cross-Dataset Data Augmentation. That is, the creation of new samples by morphing observations from a different source into credible specimens for the training dataset. Of course specific and strict conditions must be satisfied for this trick to work. In this paper we propose a general set of strategies and rules for Cross-Dataset Data Augmentation and we demonstrate its feasibility over a concrete case study. Even without defining any new formal approach, we think that the preliminary results of our paper are worth to produce a broader discussion on this topic.
2018
Proceedings - International Conference on Pattern Recognition
File in questo prodotto:
File Dimensione Formato  
2018-ICPR-learning.pdf

accesso aperto

Tipologia: Documento in Pre-print
Licenza: Accesso gratuito (solo visione)
Dimensione 446.92 kB
Formato Adobe PDF
446.92 kB Adobe PDF Visualizza/Apri

I documenti in ARCA 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/10278/3710073
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 10
  • ???jsp.display-item.citation.isi??? 7
social impact