Developmental Pretraining (DPT) for Image Classification Networks

In the backdrop of increasing data requirements of Deep Neural Networks for object recognition that is growing more untenable by the day, we present Developmental PreTraining (DPT) as a possible solution. DPT is designed as a curriculum-based pre-training approach designed to rival traditional pre-t...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-12
Main Authors: Niranjan Rajesh, Gupta, Debayan
Format: Article
Language:English
Subjects:
Artificial neural networks
Curricula
Image classification
Object recognition
Training
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 Niranjan Rajesh
Gupta, Debayan
description In the backdrop of increasing data requirements of Deep Neural Networks for object recognition that is growing more untenable by the day, we present Developmental PreTraining (DPT) as a possible solution. DPT is designed as a curriculum-based pre-training approach designed to rival traditional pre-training techniques that are data-hungry. These training approaches also introduce unnecessary features that could be misleading when the network is employed in a downstream classification task where the data is sufficiently different from the pre-training data and is scarce. We design the curriculum for DPT by drawing inspiration from human infant visual development. DPT employs a phased approach where carefully-selected primitive and universal features like edges and shapes are taught to the network participating in our pre-training regime. A model that underwent the DPT regime is tested against models with randomised weights to evaluate the viability of DPT.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2897291149</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2897291149</sourcerecordid><originalsourceid>FETCH-proquest_journals_28972911493</originalsourceid><addsrcrecordid>eNqNyrEOgjAUQNHGxESi_EMTFx1I4BUERgMaXQwDO2nMKymWFtuiv6-DH-B0h3MXJADGkqhIAVYkdG6I4xgOOWQZC8ixxhcqM42oPVe0segtl1rqnu7qpt1TYSy9jrxHWinunBTyzr00mt7Qv419uA1ZCq4chr-uyfZ8aqtLNFnznNH5bjCz1V_qoChzKJMkLdl_1wdPEzkt</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2897291149</pqid></control><display><type>article</type><title>Developmental Pretraining (DPT) for Image Classification Networks</title><source>Publicly Available Content (ProQuest)</source><creator>Niranjan Rajesh ; Gupta, Debayan</creator><creatorcontrib>Niranjan Rajesh ; Gupta, Debayan</creatorcontrib><description>In the backdrop of increasing data requirements of Deep Neural Networks for object recognition that is growing more untenable by the day, we present Developmental PreTraining (DPT) as a possible solution. DPT is designed as a curriculum-based pre-training approach designed to rival traditional pre-training techniques that are data-hungry. These training approaches also introduce unnecessary features that could be misleading when the network is employed in a downstream classification task where the data is sufficiently different from the pre-training data and is scarce. We design the curriculum for DPT by drawing inspiration from human infant visual development. DPT employs a phased approach where carefully-selected primitive and universal features like edges and shapes are taught to the network participating in our pre-training regime. A model that underwent the DPT regime is tested against models with randomised weights to evaluate the viability of DPT.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial neural networks ; Curricula ; Image classification ; Object recognition ; Training</subject><ispartof>arXiv.org, 2023-12</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (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/2897291149?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25752,37011,44589</link.rule.ids></links><search><creatorcontrib>Niranjan Rajesh</creatorcontrib><creatorcontrib>Gupta, Debayan</creatorcontrib><title>Developmental Pretraining (DPT) for Image Classification Networks</title><title>arXiv.org</title><description>In the backdrop of increasing data requirements of Deep Neural Networks for object recognition that is growing more untenable by the day, we present Developmental PreTraining (DPT) as a possible solution. DPT is designed as a curriculum-based pre-training approach designed to rival traditional pre-training techniques that are data-hungry. These training approaches also introduce unnecessary features that could be misleading when the network is employed in a downstream classification task where the data is sufficiently different from the pre-training data and is scarce. We design the curriculum for DPT by drawing inspiration from human infant visual development. DPT employs a phased approach where carefully-selected primitive and universal features like edges and shapes are taught to the network participating in our pre-training regime. A model that underwent the DPT regime is tested against models with randomised weights to evaluate the viability of DPT.</description><subject>Artificial neural networks</subject><subject>Curricula</subject><subject>Image classification</subject><subject>Object recognition</subject><subject>Training</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNyrEOgjAUQNHGxESi_EMTFx1I4BUERgMaXQwDO2nMKymWFtuiv6-DH-B0h3MXJADGkqhIAVYkdG6I4xgOOWQZC8ixxhcqM42oPVe0segtl1rqnu7qpt1TYSy9jrxHWinunBTyzr00mt7Qv419uA1ZCq4chr-uyfZ8aqtLNFnznNH5bjCz1V_qoChzKJMkLdl_1wdPEzkt</recordid><startdate>20231201</startdate><enddate>20231201</enddate><creator>Niranjan Rajesh</creator><creator>Gupta, Debayan</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>20231201</creationdate><title>Developmental Pretraining (DPT) for Image Classification Networks</title><author>Niranjan Rajesh ; Gupta, Debayan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28972911493</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial neural networks</topic><topic>Curricula</topic><topic>Image classification</topic><topic>Object recognition</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Niranjan Rajesh</creatorcontrib><creatorcontrib>Gupta, Debayan</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</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 (ProQuest)</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>Niranjan Rajesh</au><au>Gupta, Debayan</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Developmental Pretraining (DPT) for Image Classification Networks</atitle><jtitle>arXiv.org</jtitle><date>2023-12-01</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>In the backdrop of increasing data requirements of Deep Neural Networks for object recognition that is growing more untenable by the day, we present Developmental PreTraining (DPT) as a possible solution. DPT is designed as a curriculum-based pre-training approach designed to rival traditional pre-training techniques that are data-hungry. These training approaches also introduce unnecessary features that could be misleading when the network is employed in a downstream classification task where the data is sufficiently different from the pre-training data and is scarce. We design the curriculum for DPT by drawing inspiration from human infant visual development. DPT employs a phased approach where carefully-selected primitive and universal features like edges and shapes are taught to the network participating in our pre-training regime. A model that underwent the DPT regime is tested against models with randomised weights to evaluate the viability of DPT.</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, 2023-12
issn 2331-8422
language eng
recordid cdi_proquest_journals_2897291149
source Publicly Available Content (ProQuest)
subjects Artificial neural networks
Curricula
Image classification
Object recognition
Training
title Developmental Pretraining (DPT) for Image Classification Networks
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T23%3A08%3A16IST&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=Developmental%20Pretraining%20(DPT)%20for%20Image%20Classification%20Networks&rft.jtitle=arXiv.org&rft.au=Niranjan%20Rajesh&rft.date=2023-12-01&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2897291149%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_28972911493%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2897291149&rft_id=info:pmid/&rfr_iscdi=true