.png){kind=icon}
返回
Deep FisherNet for Image Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2018.2874657.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
Keyword:
Convolutional neural networks (CNNs)
end to end
Fisher layer
Fisher vector (FV)
image classification
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
分享收藏Co-trained convolutional neural networks for automated detection of prostate cancer in multi-parametric MRI.png)
MEDICAL IMAGE ANALYSIS
MEDICAL IMAGE ANALYSISIF11.8
PREAI
分享收藏Comparative study of layer by layer assembled multilayer films based on graphene oxide and reduced graphene oxide on flexible polyurethane foam: flame retardant and smoke suppression propertiesRSC Advances
RSC AdvancesIF0
PREAI
分享收藏
查看更多内容