Files in this item

FilesDescriptionFormat

application/pdf

application/pdfECe499-Sp2018-yu-Lian.pdf (1MB)Restricted to U of Illinois
(no description provided)PDF

Description

Title:Analysis of the two-part predictive coder
Author(s):Yu, Lian
Contributor(s):Moulin, Pierre
Subject(s):Image Compression
Image Classification
Predictive Coding
Neural Networks
Abstract:The two-part predictive coding framework aims to compress signals while preserving feature quality for analysis purposes. The change in feature vectors after the compression is treated as a prediction error and is quantized using a classification centric quantizer. The classification centric quantizer is a vector quantizer that minimizes classification error in the task of image classification. In this thesis, the method is applied to the STL-10 dataset and a subset of the ILSVRC2012 dataset. The classification systems include a deep hybrid neural network that consists of the scattering transform and the residual network, and an end-to-end learned deep residual network.
Issue Date:2018-05
Genre:Other
Type:Text
Language:English
URI:http://hdl.handle.net/2142/100059
Date Available in IDEALS:2018-05-30


This item appears in the following Collection(s)

Item Statistics