Publications
Authors:
  • Zeynep Akata , Florent Perronnin , Zaid Harchaoui , Schmid Cordelia
Citation:
Neural Information Processing Systems Conference and Workshops, Lake Tahoe, Nevada, USA, December 5-10, 2013.
Abstract:
Attributes are an intermediate representation whose purpose is to enable parameter sharing between classes, a must when training data is scarce. We propose
to view attribute-based image classification as a label-embedding problem: each
class is embedded in the space of attribute vectors. We introduce a function which
measures the compatibility between an image and a label embedding. The parameters of this function are learned on a training set of labeled samples to ensure that,
given an image. the correct class has a higher compatibility than the incorrect ones.
Experimental results on two standard image classification datasets arc presented,
resp. on the Animals With Attributes and on Caltech—UCSD—Birds datasets.
Year:
2013
Report number:
2013/052