Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Optimization of robust loss functions for weakly-labeled image taxonomies

Autor
McAuley, J.; Ramisa, A.; Caetano, T.
Tipus d'activitat
Article en revista
Revista
International journal of computer vision
Data de publicació
2013
Volum
104
Número
3
Pàgina inicial
343
Pàgina final
361
DOI
https://doi.org/10.1007/s11263-012-0561-4 Obrir en finestra nova
Repositori
http://hdl.handle.net/2117/20202 Obrir en finestra nova
Resum
The recently proposed ImageNet dataset consists of several million images, each annotated with a single object category. These annotations may be imperfect, in the sense that many images contain multiple objects belonging to the label vocabulary. In other words, we have a multi-label problem but the annotations include only a single label (which is not necessarily the most prominent). Such a setting motivates the use of a robust evaluation measure, which allows for a limited number of labels to ...
Citació
McAuley, J.; Ramisa, A.; Caetano, T. Optimization of robust loss functions for weakly-labeled image taxonomies. "International journal of computer vision", 2013, vol. 104, núm. 3, p. 343-361.
Paraules clau
Computer Vision, Image Classification, Object Recognition, Optimisation Paraules Autor: Image Labeling, Image Tagging, Image Taxonomies, Structured Learning

Participants

  • McAuley, Julian J.  (autor)
  • Ramisa Ayats, Arnau  (autor)
  • Caetano, Tibério S.  (autor)