- 1、本文档共24页,可阅读全部内容。
- 2、有哪些信誉好的足球投注网站(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。
- 3、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
查看更多
Deep Generative Deconvolutional Image Model
A Deep Generative Deconvolutional Image Model
Yunchen Pu Xin Yuan Andrew Stevens Chunyuan Li Lawrence Carin
Duke University Bell Labs Duke University Duke University Duke University
Abstract
A deep generative model is developed for rep-
resentation and analysis of images, based on
a hierarchical convolutional dictionary-learning
framework. Stochastic unpooling is employed
to link consecutive layers in the model, yielding
top-down image generation. A Bayesian support
vector machine is linked to the top-layer features,
yielding max-margin discrimination. Deep de-
convolutional inference is employed when test-
ing, to infer the latent features, and the top-layer
features are connected with the max-margin clas-
sifier for discrimination tasks. The model is effi-
ciently trained using a Monte Carlo expectation-
maximization (MCEM) algorithm, with imple-
mentation on graphical processor units (GPUs)
for efficient large-scale learning, and fast testing.
Excellent results are obtained on several bench-
mark datasets, including ImageNet, demonstrat-
ing that the proposed model achieves results that
are highly competitive with similarly sized con-
volutional neural networks.
1 Introduction
Convolutional neural networks (CNN) (LeCun et al., 1989)
are effective tools for image and video analysis (Chatfield
et al., 2014; Krizhevsky et al., 2012; Mnih et al., 2013; Ser-
manet et al., 2013). The CNN is characterized by feedfor-
ward (bottom-up) sequential application of convolutional
filterbanks, pointwise nonlinear functions (e.g., sigmoid or
hyperbolic tangent), and pooling. Supervision in CNN is
typically implemented via a fully-connected layer at the
top of the deep architecture, usually with a softmax clas-
sifier (Ciresan et al., 2011; He et al., 2014; Jarrett et al.,
2009; Krizhevsky et al., 2012).
A parallel line of research concerns dictionary learning
Appearing in Proceedings of the 19th International Conference
on Artificial Intelligence and Statistics (AISTATS) 2016, C
您可能关注的文档
- Charm counting and B semileptonic branching fraction.pdf
- Charmed Meson Production in Proton - (ANTI)PROTON Collisions.pdf
- Charm Results on CP Violation and Mixing.pdf
- Charmonium and CharmSpectroscopyat the e+e- B-Factories.ppt
- chatra kalyan rules.pdf
- chemical priming with urea and KNO3 enhances maiz hybids seed viability under abiotic stress.pdf
- chemical safety of meat products.pdf
- CHATTERBOX BOOK 4(1-2单元).pdf
- Chemical characterization and source apportionment of PM2.5.pdf
- Chemically modified light-curable chitosans with enhanced.pdf
文档评论(0)