Fisher Vectors Meet Neural Networks: A Hybrid Classification Architecture
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.
Cite
Text
Perronnin and Larlus. "Fisher Vectors Meet Neural Networks: A Hybrid Classification Architecture." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7298998Markdown
[Perronnin and Larlus. "Fisher Vectors Meet Neural Networks: A Hybrid Classification Architecture." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/perronnin2015cvpr-fisher/) doi:10.1109/CVPR.2015.7298998BibTeX
@inproceedings{perronnin2015cvpr-fisher,
title = {{Fisher Vectors Meet Neural Networks: A Hybrid Classification Architecture}},
author = {Perronnin, Florent and Larlus, Diane},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2015},
doi = {10.1109/CVPR.2015.7298998},
url = {https://mlanthology.org/cvpr/2015/perronnin2015cvpr-fisher/}
}