Deep FisherNet for Object Classification
This work addresses object classification challenges in computer vision, offering a hybrid method that combines existing techniques for incremental gains.
The authors tackled the problem of object classification on images with large variation in size and clutter by proposing FisherNet, which integrates Fisher Vector encoding into a CNN in an end-to-end trainable system. They achieved improved classification accuracy and computational efficiency on the PASCAL VOC dataset compared to plain CNNs and standard FV.
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.