Since the advent of deep learning, neural networks have demonstrated remarkable results in many visual recognition tasks, constantly pushing the limits. However, the state of-the-art approaches are largely unsuitable in scarce data regimes. To address this shortcoming, this paper proposes employing a 3D model, which is derived from training images. Such a model can then be used to hallucinate novel viewpoints and poses for the scarce samples of the few-shot learning scenario. A self-paced learning approach allows for the selection of a diverse set of high-quality images, which facilitates the training of a classifier. The performance of the proposed approach is showcased on the fine grained CUB-200-2011 dataset in a few-shot setting and significantly improves our baseline accuracy.

Low-shot learning from imaginary 3D model / Pahde, F.; Puscas, M.; Wolff, J.; Klein, T.; Sebe, N.; Nabi, N. M.. - (2019), pp. 978-985. (Intervento presentato al convegno IEEE Winter Conference on Application of Computer Vision tenutosi a Hawaii nel 7-11 January , 2019) [10.1109/WACV.2019.00109].

Low-shot learning from imaginary 3D model

M. Puscas;N. Sebe;
2019-01-01

Abstract

Since the advent of deep learning, neural networks have demonstrated remarkable results in many visual recognition tasks, constantly pushing the limits. However, the state of-the-art approaches are largely unsuitable in scarce data regimes. To address this shortcoming, this paper proposes employing a 3D model, which is derived from training images. Such a model can then be used to hallucinate novel viewpoints and poses for the scarce samples of the few-shot learning scenario. A self-paced learning approach allows for the selection of a diverse set of high-quality images, which facilitates the training of a classifier. The performance of the proposed approach is showcased on the fine grained CUB-200-2011 dataset in a few-shot setting and significantly improves our baseline accuracy.
2019
IEEE Winter Conference on Application of Computer Vision
New York
IEEE
Pahde, F.; Puscas, M.; Wolff, J.; Klein, T.; Sebe, N.; Nabi, N. M.
Low-shot learning from imaginary 3D model / Pahde, F.; Puscas, M.; Wolff, J.; Klein, T.; Sebe, N.; Nabi, N. M.. - (2019), pp. 978-985. (Intervento presentato al convegno IEEE Winter Conference on Application of Computer Vision tenutosi a Hawaii nel 7-11 January , 2019) [10.1109/WACV.2019.00109].
File in questo prodotto:
File Dimensione Formato  
08659127.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.03 MB
Formato Adobe PDF
1.03 MB Adobe PDF   Visualizza/Apri
1901.01868.pdf

Open Access dal 05/01/2021

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 5.86 MB
Formato Adobe PDF
5.86 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/11572/250714
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 2
social impact