Back to Search
Start Over
Deep FisherNet for Image Classification.
- Source :
- IEEE Transactions on Neural Networks & Learning Systems; Jul2019, Vol. 30 Issue 7, p2244-2250, 7p
- Publication Year :
- 2019
-
Abstract
- Despite the great success of convolutional neural networks (CNNs) for the image classification task on data sets such as Cifar and ImageNet, CNN’s representation power is still somewhat limited in dealing with images that have a large variation in size and clutter, where Fisher vector (FV) has shown to be an effective encoding strategy. FV encodes an image by aggregating local descriptors with a universal generative Gaussian mixture model (GMM). FV, however, has limited learning capability and its parameters are mostly fixed after constructing the codebook. To combine together the best of the two worlds, we propose in this brief a neural network structure with FV layer being part of an end-to-end trainable system that is differentiable; we name our network FisherNet that is learnable using back propagation. Our proposed FisherNet combines CNN training and FV encoding in a single end-to-end structure. We observe a clear advantage of FisherNet over plain CNN and standard FV in terms of both classification accuracy and computational efficiency on the challenging PASCAL visual object classes object classification and emotion image classification tasks. [ABSTRACT FROM AUTHOR]
- Subjects :
- GAUSSIAN mixture models
BACK propagation
CLASSIFICATION
ARTIFICIAL neural networks
Subjects
Details
- Language :
- English
- ISSN :
- 2162237X
- Volume :
- 30
- Issue :
- 7
- Database :
- Complementary Index
- Journal :
- IEEE Transactions on Neural Networks & Learning Systems
- Publication Type :
- Periodical
- Accession number :
- 137117522
- Full Text :
- https://doi.org/10.1109/TNNLS.2018.2874657