Deep FisherNet for Object Classification

TL;DR

This paper introduces FisherNet, an end-to-end trainable neural network that integrates Fisher Vector encoding with CNNs, improving object classification accuracy and efficiency on challenging datasets.

Contribution

FisherNet combines CNN training with Fisher Vector encoding in a differentiable, end-to-end system, enhancing object classification performance.

Findings

FisherNet outperforms plain CNN and standard FV in accuracy.

FisherNet is more computationally efficient.

FisherNet demonstrates superior results on PASCAL VOC dataset.

Abstract

Despite the great success of convolutional neural networks (CNN) for the image classification task on datasets like Cifar and ImageNet, CNN's representation power is still somewhat limited in dealing with object images that have 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 paper 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 backpropagation. Our proposed FisherNet combines convolutional neural network training and Fisher Vector 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 VOC object classification task.