Publications
Authors:
  • Florent Perronnin , Diane Larlus
Citation:
CVPR, Boston, USA, 7-12 June, 2015
Abstract:
Fisher Vectors (FV) and Convolutional Neural Networks
(CNN) are two image classification pipelines with different
strengths. While CNNs have shown superior accuracy on
a number of classification tasks, FV classifiers are typically
less costly to train and evaluate. We propose a hybrid architecture
that combines their strengths: the first unsupervised
layers rely on the FV while the subsequent fully-connected
supervised layers are trained with back-propagation. We
show experimentally that this hybrid architecture significantly
outperforms standard FV systems without incurring
the high cost that comes with CNNs. We also derive competitive
mid-level features from our architecture that are readily
applicable to other class sets and even to new tasks.
Year:
2015
Report number:
2015/020