Learning Categories From Few Examples With Multi Model Knowledge Transfer

Learning a visual object category from few samples is a compelling and challenging problem. In several real-world applications collecting many annotated data is costly and not always possible. However, a small training set does not allow to cover the high intraclass variability typical of visual obj...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 36(2014), 5 vom: 01. Mai, Seite 928-41
1. Verfasser: Tommasi, Tatiana (VerfasserIn)
Weitere Verfasser: Orabona, Francesco, Caputo, Barbara
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2014
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM252591038
003 DE-627
005 20231224164432.0
007 cr uuu---uuuuu
008 231224s2014 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2013.197  |2 doi 
028 5 2 |a pubmed24n0842.xml 
035 |a (DE-627)NLM252591038 
035 |a (NLM)26353227 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Tommasi, Tatiana  |e verfasserin  |4 aut 
245 1 0 |a Learning Categories From Few Examples With Multi Model Knowledge Transfer 
264 1 |c 2014 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 25.11.2015 
500 |a Date Revised 10.09.2015 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Learning a visual object category from few samples is a compelling and challenging problem. In several real-world applications collecting many annotated data is costly and not always possible. However, a small training set does not allow to cover the high intraclass variability typical of visual objects. In this condition, machine learning methods provide very few guarantees. This paper presents a discriminative model adaptation algorithm able to proficiently learn a target object with few examples by relying on other previously learned source categories. The proposed method autonomously chooses from where and how much to transfer information by solving a convex optimization problem which ensures to have the minimal leave-one-out error on the available training set. We analyze several properties of the described approach and perform an extensive experimental comparison with other existing transfer solutions, consistently showing the value of our algorithm 
650 4 |a Journal Article 
700 1 |a Orabona, Francesco  |e verfasserin  |4 aut 
700 1 |a Caputo, Barbara  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 36(2014), 5 vom: 01. Mai, Seite 928-41  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:36  |g year:2014  |g number:5  |g day:01  |g month:05  |g pages:928-41 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2013.197  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 36  |j 2014  |e 5  |b 01  |c 05  |h 928-41