<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-22T17:49:09Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/16692" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/16692</identifier><datestamp>2025-03-26T23:32:30Z</datestamp><setSpec>com_10012_9900</setSpec><setSpec>com_10012_1</setSpec><setSpec>col_10012_9908</setSpec><setSpec>col_10012_6</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:doc="http://www.lyncode.com/xoai" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Yang, En-hui</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author" authority="13f76adf-b3de-4232-a075-02b3d80e6898">Shaterian Bidgoli, Sepideh</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2021-01-18T20:57:04Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2021-01-18T20:57:04Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2021-01-18</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2021-01-13</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/10012/16692</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en">Deep Neural Networks (DNNs) demonstrate excellent performance in many Computer Vision&#xd;
(CV) applications such as image classification. To meet storage/bandwidth requirements,&#xd;
the input images to these CV applications are compressed using lossy image compression standards,&#xd;
among which JPEG is the most common. Classical JPEG is designed to consider Human&#xd;
Vision (HV) and pays a little attention to CV, resulting in classification accuracy drop of DNNs,&#xd;
especially at high Compression Ratios (CRs). This work presents Deep Selector-JPEG, an adaptive&#xd;
JPEG compression method that simultaneously targets both image classification and HV. For&#xd;
each image, Deep Selector-JPEG selects a Quality Factor (QF) adaptively to compress the image&#xd;
so that a good trade-off between the Compression Ratio (CR) and DNN classifier Accuracy&#xd;
(Rate-Accuracy performance) can be achieved over a set of images for a variety of DNN classifiers&#xd;
while the PSNR of such compressed image is greater than a threshold value predetermined&#xd;
by HV with a high probability.&#xd;
Towards this end, Deep Selector-JPEG first defines a set of feasible QFs such that an image&#xd;
compressed at any QF within this set has PSNR greater than a predetermined threshold value&#xd;
with a high probability. For some images, multiple QFs within this set are suitable (ON) for&#xd;
compressing for a DNN classifier, which means compressing at these QFs at least maintains&#xd;
the ground truth rank of the original input for the DNN classifier. For a given image, Deep&#xd;
Selector-JPEG first determines the QFs that are ON among the set of feasible QFs. This problem&#xd;
is represented as a Multi-label Classification (MLC) problem since each image has multiple&#xd;
corresponding suitable QFs. We solve MLC using a binary relevance procedure, which involves&#xd;
training an independent binary DNN classifier for each QF within the feasible set to predict the&#xd;
ON/OFF labeling for each input image. Given a target CR, we empirically derive a subset of&#xd;
feasible QFs for this target CR and select the least QF that is ON in this set.&#xd;
Experimental results show that in comparison with the default JPEG, Deep Selector-JPEG&#xd;
indeed achieves better Rate-Accuracy performance over the entire ImageNet validation set for&#xd;
all tested DNN classifiers with gains in classification accuracy up to  1% at the same CRs, while&#xd;
satisfying HV constraints and keeping complexity under control.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en">en</dim:field>
   <dim:field mdschema="dc" element="publisher" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">computer vision</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">deep learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">image compression</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">image processing</dim:field>
   <dim:field mdschema="dc" element="title" lang="en">Deep SELECTOR-JPEG: ADAPTIVE JPEG IMAGE COMPRESSION FOR COMPUTER VISION IN IMAGE CLASSIFICATION AND HUMAN VISION</dim:field>
   <dim:field mdschema="dc" element="type" lang="en">Master Thesis</dim:field>
   <dim:field mdschema="dc" element="pending">false</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="department" lang="en">Electrical and Computer Engineering</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="discipline" lang="en">Electrical and Computer Engineering</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="grantor" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="uws-etd" element="degree" lang="en">Master of Applied Science</dim:field>
   <dim:field mdschema="uws-etd" element="embargo" qualifier="terms" lang="en">0</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="advisor">Yang, En-hui</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="affiliation1" lang="en">Faculty of Engineering</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="city" lang="en">Waterloo</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="country" lang="en">Canada</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="province" lang="en">Ontario</dim:field>
   <dim:field mdschema="uws" element="typeOfResource" lang="en">Text</dim:field>
   <dim:field mdschema="uws" element="peerReviewStatus" lang="en">Unreviewed</dim:field>
   <dim:field mdschema="uws" element="scholarLevel" lang="en">Graduate</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>