Learning Image Relations with Contrast Association Networks

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussavertaisarvioitu

Tutkijat

Organisaatiot

  • Australian National University
  • Norwegian University of Science and Technology

Kuvaus

Inferring the relations between two images is an important class of tasks in computer vision. Examples of such tasks include computing optical flow and stereo disparity. We treat the relation inference tasks as a machine learning problem and tackle it with neural networks. A key to the problem is learning a representation of relations. We propose a new neural network module, contrast association unit (CAU), which explicitly models the relations between two sets of input variables. Due to the non-negativity of the weights in CAU, we adopt a multiplicative update algorithm for learning these weights. Experiments show that neural networks with CAUs are more effective in learning five fundamental image transformations than conventional neural networks.

Yksityiskohdat

AlkuperäiskieliEnglanti
Otsikko2019 International Joint Conference on Neural Networks, IJCNN 2019
TilaJulkaistu - 1 heinäkuuta 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaInternational Joint Conference on Neural Networks - Budapest, Unkari
Kesto: 14 heinäkuuta 201919 heinäkuuta 2019

Julkaisusarja

NimiProceedings of the International Joint Conference on Neural Networks
Vuosikerta2019-July

Conference

ConferenceInternational Joint Conference on Neural Networks
LyhennettäIJCNN
MaaUnkari
KaupunkiBudapest
Ajanjakso14/07/201919/07/2019

ID: 39155199