Loading…
Increasing the Accuracy of a Neural Network Using Frequency Selective Mesh-to-Grid Resampling
Neural networks are widely used for almost any task of recognizing image content. Even though much effort has been put into investigating efficient network architectures, optimizers, and training strategies, the influence of image interpolation on the performance of neural networks is not well studi...
Saved in:
Published in: | arXiv.org 2022-09 |
---|---|
Main Authors: | , , |
Format: | Article |
Language: | English |
Subjects: | |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | |
---|---|
cites | |
container_end_page | |
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Spruck, Andreas Heimann, Viktoria Kaup, André |
description | Neural networks are widely used for almost any task of recognizing image content. Even though much effort has been put into investigating efficient network architectures, optimizers, and training strategies, the influence of image interpolation on the performance of neural networks is not well studied. Furthermore, research has shown that neural networks are often sensitive to minor changes in the input image leading to drastic drops of their performance. Therefore, we propose the use of keypoint agnostic frequency selective mesh-to-grid resampling (FSMR) for the processing of input data for neural networks in this paper. This model-based interpolation method already showed that it is capable of outperforming common interpolation methods in terms of PSNR. Using an extensive experimental evaluation we show that depending on the network architecture and classification task the application of FSMR during training aids the learning process. Furthermore, we show that the usage of FSMR in the application phase is beneficial. The classification accuracy can be increased by up to 4.31 percentage points for ResNet50 and the Oxflower17 dataset. |
format | article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2719595290</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2719595290</sourcerecordid><originalsourceid>FETCH-proquest_journals_27195952903</originalsourceid><addsrcrecordid>eNqNzEsKwjAYBOAgCBbtHQKuA2lqrF2KWHWhCx9LKSH-ta01qUmqeHuDeABXwzAf00MBi-OIzCaMDVBobU0pZdOEcR4H6LxR0oCwlbpiVwKeS9kZId9YF1jgHfjS-HAvbW749GWZgUcHypsDNCBd9QS8BVsSp8nKVBe8ByvubePtCPUL0VgIfzlE42x5XKxJa7T_sC6vdWeUn3KWRClPOUtp_J_6AMEHQ1g</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2719595290</pqid></control><display><type>article</type><title>Increasing the Accuracy of a Neural Network Using Frequency Selective Mesh-to-Grid Resampling</title><source>Publicly Available Content Database</source><creator>Spruck, Andreas ; Heimann, Viktoria ; Kaup, André</creator><creatorcontrib>Spruck, Andreas ; Heimann, Viktoria ; Kaup, André</creatorcontrib><description>Neural networks are widely used for almost any task of recognizing image content. Even though much effort has been put into investigating efficient network architectures, optimizers, and training strategies, the influence of image interpolation on the performance of neural networks is not well studied. Furthermore, research has shown that neural networks are often sensitive to minor changes in the input image leading to drastic drops of their performance. Therefore, we propose the use of keypoint agnostic frequency selective mesh-to-grid resampling (FSMR) for the processing of input data for neural networks in this paper. This model-based interpolation method already showed that it is capable of outperforming common interpolation methods in terms of PSNR. Using an extensive experimental evaluation we show that depending on the network architecture and classification task the application of FSMR during training aids the learning process. Furthermore, we show that the usage of FSMR in the application phase is beneficial. The classification accuracy can be increased by up to 4.31 percentage points for ResNet50 and the Oxflower17 dataset.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Classification ; Computer architecture ; Finite element method ; Interpolation ; Neural networks ; Object recognition ; Resampling ; Training</subject><ispartof>arXiv.org, 2022-09</ispartof><rights>2022. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2719595290?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Spruck, Andreas</creatorcontrib><creatorcontrib>Heimann, Viktoria</creatorcontrib><creatorcontrib>Kaup, André</creatorcontrib><title>Increasing the Accuracy of a Neural Network Using Frequency Selective Mesh-to-Grid Resampling</title><title>arXiv.org</title><description>Neural networks are widely used for almost any task of recognizing image content. Even though much effort has been put into investigating efficient network architectures, optimizers, and training strategies, the influence of image interpolation on the performance of neural networks is not well studied. Furthermore, research has shown that neural networks are often sensitive to minor changes in the input image leading to drastic drops of their performance. Therefore, we propose the use of keypoint agnostic frequency selective mesh-to-grid resampling (FSMR) for the processing of input data for neural networks in this paper. This model-based interpolation method already showed that it is capable of outperforming common interpolation methods in terms of PSNR. Using an extensive experimental evaluation we show that depending on the network architecture and classification task the application of FSMR during training aids the learning process. Furthermore, we show that the usage of FSMR in the application phase is beneficial. The classification accuracy can be increased by up to 4.31 percentage points for ResNet50 and the Oxflower17 dataset.</description><subject>Classification</subject><subject>Computer architecture</subject><subject>Finite element method</subject><subject>Interpolation</subject><subject>Neural networks</subject><subject>Object recognition</subject><subject>Resampling</subject><subject>Training</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNzEsKwjAYBOAgCBbtHQKuA2lqrF2KWHWhCx9LKSH-ta01qUmqeHuDeABXwzAf00MBi-OIzCaMDVBobU0pZdOEcR4H6LxR0oCwlbpiVwKeS9kZId9YF1jgHfjS-HAvbW749GWZgUcHypsDNCBd9QS8BVsSp8nKVBe8ByvubePtCPUL0VgIfzlE42x5XKxJa7T_sC6vdWeUn3KWRClPOUtp_J_6AMEHQ1g</recordid><startdate>20220928</startdate><enddate>20220928</enddate><creator>Spruck, Andreas</creator><creator>Heimann, Viktoria</creator><creator>Kaup, André</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20220928</creationdate><title>Increasing the Accuracy of a Neural Network Using Frequency Selective Mesh-to-Grid Resampling</title><author>Spruck, Andreas ; Heimann, Viktoria ; Kaup, André</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27195952903</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Classification</topic><topic>Computer architecture</topic><topic>Finite element method</topic><topic>Interpolation</topic><topic>Neural networks</topic><topic>Object recognition</topic><topic>Resampling</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Spruck, Andreas</creatorcontrib><creatorcontrib>Heimann, Viktoria</creatorcontrib><creatorcontrib>Kaup, André</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Spruck, Andreas</au><au>Heimann, Viktoria</au><au>Kaup, André</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Increasing the Accuracy of a Neural Network Using Frequency Selective Mesh-to-Grid Resampling</atitle><jtitle>arXiv.org</jtitle><date>2022-09-28</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Neural networks are widely used for almost any task of recognizing image content. Even though much effort has been put into investigating efficient network architectures, optimizers, and training strategies, the influence of image interpolation on the performance of neural networks is not well studied. Furthermore, research has shown that neural networks are often sensitive to minor changes in the input image leading to drastic drops of their performance. Therefore, we propose the use of keypoint agnostic frequency selective mesh-to-grid resampling (FSMR) for the processing of input data for neural networks in this paper. This model-based interpolation method already showed that it is capable of outperforming common interpolation methods in terms of PSNR. Using an extensive experimental evaluation we show that depending on the network architecture and classification task the application of FSMR during training aids the learning process. Furthermore, we show that the usage of FSMR in the application phase is beneficial. The classification accuracy can be increased by up to 4.31 percentage points for ResNet50 and the Oxflower17 dataset.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2022-09 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2719595290 |
source | Publicly Available Content Database |
subjects | Classification Computer architecture Finite element method Interpolation Neural networks Object recognition Resampling Training |
title | Increasing the Accuracy of a Neural Network Using Frequency Selective Mesh-to-Grid Resampling |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T03%3A15%3A39IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Increasing%20the%20Accuracy%20of%20a%20Neural%20Network%20Using%20Frequency%20Selective%20Mesh-to-Grid%20Resampling&rft.jtitle=arXiv.org&rft.au=Spruck,%20Andreas&rft.date=2022-09-28&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2719595290%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_27195952903%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2719595290&rft_id=info:pmid/&rfr_iscdi=true |