Attributes have shown great potential in visual recognition recently since they, as mid-level features, can be shared across different categories. However, existing attribute learning methods are prone to learning the correlated attributes which results in the difficulties of selecting attribute specific features. In this paper, we propose an attribute specific dictionary learning approach to address this issue. Category information is incorporated into our framework while learning the over-complete dictionary, which encourages the samples from the same category to have similar distributions over the dictionary bases. A novel scheme is developed to select the attribute specific dictionaries. The attribute specific dictionary consists of the bases which are only shared among the positive samples or the negative samples. The experiments on the Animals with Attributes (AwA) dataset show the effectiveness of our proposed method.

Attribute Guided Dictionary Learning / Wang, Wei; Yan, Yan; Sebe, Niculae. - (2015), pp. 211-218. ((Intervento presentato al convegno ICMR 2015 tenutosi a Shanghai nel 23th-26th June, 2015 [10.1145/2671188.2749337].

Attribute Guided Dictionary Learning

Wang, Wei;Yan, Yan;Sebe, Niculae
2015

Abstract

Attributes have shown great potential in visual recognition recently since they, as mid-level features, can be shared across different categories. However, existing attribute learning methods are prone to learning the correlated attributes which results in the difficulties of selecting attribute specific features. In this paper, we propose an attribute specific dictionary learning approach to address this issue. Category information is incorporated into our framework while learning the over-complete dictionary, which encourages the samples from the same category to have similar distributions over the dictionary bases. A novel scheme is developed to select the attribute specific dictionaries. The attribute specific dictionary consists of the bases which are only shared among the positive samples or the negative samples. The experiments on the Animals with Attributes (AwA) dataset show the effectiveness of our proposed method.
ICMR '15: Proceedings of the 5th ACM on International Conference on Multimedia Retrieval
New York, NY
ACM
9781450332743
Wang, Wei; Yan, Yan; Sebe, Niculae
Attribute Guided Dictionary Learning / Wang, Wei; Yan, Yan; Sebe, Niculae. - (2015), pp. 211-218. ((Intervento presentato al convegno ICMR 2015 tenutosi a Shanghai nel 23th-26th June, 2015 [10.1145/2671188.2749337].
File in questo prodotto:
File Dimensione Formato  
Wei-ICMR15.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 2.58 MB
Formato Adobe PDF
2.58 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/11572/115057
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 12
  • ???jsp.display-item.citation.isi??? 7
social impact