Backpropagation Training for Fisher Vectors within Neural Networks

2017-02-08 · Patrick Wieschollek, Fabian Groh, Hendrik P. A. Lensch

Fisher-Vectors (FV) encode higher-order statistics of a set of multiple local descriptors like SIFT features. They already show good performance in combination with shallow learning architectures on visual recognitions tasks. Current methods using FV as a feature descriptor in deep architectures assume that all original input features are static. We propose a framework to jointly learn the representation of original features, FV parameters and parameters of the classifier in the style of traditional neural networks. Our proof of concept implementation improves the performance of FV on the Pascal Voc 2007 challenge in a multi-GPU setting in comparison to a default SVM setting. We demonstrate that FV can be embedded into neural networks at arbitrary positions, allowing end-to-end training with back-propagation.

📄 PDF Abstract BibTeX arXiv:1702.02549

Code (0)

등록된 구현이 없습니다.

Tasks

GPU

Methods 이 논문이 사용한 방법론

SVM A Support Vector Machine, or SVM, is a non-parametric supervised learning model. For non-linear classification and regression, they utilise the kernel trick to map inputs…

RNN Fisher Vectors for Action Recognition and Image Annotation

2015-12-12 · Guy Lev, Gil Sadeh, Benjamin Klein, Lior Wolf

Recurrent Neural Networks (RNNs) have had considerable success in classifying and predicting sequences. We demonstrate that RNNs can be effectively used in order to encode sequences and provide effective representations.…

Action Recognition Temporal Action Localization Transfer Learning

Label Consistent Fisher Vectors for Supervised Feature Aggregation

2014-08-24 · 2014 22nd International Conference on Pattern Recognition 2014 8 · Quan Wang, Xin Shen, Meng Wang, Kim L. Boyer

In this paper, we present a simple and efficient way to add supervised information into Fisher vectors, which has become a popular image representation method for image classification and retrieval purposes in recent yea…

Classification General Classification image-classification Image Classification+1

Hyper-Fisher Vectors for Action Recognition

2015-09-28 · Sanath Narayan, Kalpathi R. Ramakrishnan

In this paper, a novel encoding scheme combining Fisher vector and bag-of-words encodings has been proposed for recognizing action in videos. The proposed Hyper-Fisher vector encoding is sum of local Fisher vectors which…

Action Recognition Temporal Action Localization

Deep FisherNet for Object Classification

2016-07-31 · Peng Tang, Xinggang Wang, Baoguang Shi, Xiang Bai 외

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 t…

Classification Computational Efficiency General Classification image-classification+2

Learning Local Feature Aggregation Functions with Backpropagation

2017-06-26 · Angelos Katharopoulos, Despoina Paschalidou, Christos Diou, Anastasios Delopoulos

This paper introduces a family of local feature aggregation functions and a novel method to estimate their parameters, such that they generate optimal representations for classification (or any task that can be expressed…

General Classification