Unsupervised Learning on Neural Network Outputs: with Application in Zero-shot Learning

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussavertaisarvioitu

Tutkijat

Organisaatiot

Kuvaus

The outputs of a trained neural network contain much richer information than just a one-hot classifier. For example, a neural network might give an image of a dog the probability of one in a million of being a cat but it is still much larger than the probability of being a car. To reveal the hidden structure in them, we apply two unsupervised learning algorithms, PCA and ICA, to the outputs of a deep Convolutional Neural Network trained on the ImageNet of 1000 classes. The PCA/ICA embedding of the object classes reveals their visual similarity and the PCA/ICA components can be interpreted as common visual features shared by similar object classes. For an application, we proposed a new zero-shot learning method, in which the visual features learned by PCA/ICA are employed. Our zeroshot learning method achieves the state-of-the-art results on the ImageNet of over 20000 classes.

Yksityiskohdat

AlkuperäiskieliEnglanti
OtsikkoProceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence
AlaotsikkoNew York, New York, USA, 9–15 July 2016
ToimittajatSubbarao Kambhampati
TilaJulkaistu - 9 heinäkuuta 2016
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaInternational Joint Conference on Artificial Intelligence - New York Hilton Midtown, New York, Yhdysvallat
Kesto: 9 heinäkuuta 201615 heinäkuuta 2016
Konferenssinumero: 25
http://ijcai-16.org/index.php/welcome/view/home

Julkaisusarja

NimiInternational Joint Conferences on Artificial Intelligence
KustantajaIAAA press
ISSN (elektroninen)1045-0823

Conference

ConferenceInternational Joint Conference on Artificial Intelligence
LyhennettäIJCAI
MaaYhdysvallat
KaupunkiNew York
Ajanjakso09/07/201615/07/2016
www-osoite

ID: 9411989