Loading…
Deep Adaptive Wavelet Network
Even though convolutional neural networks have become the method of choice in many fields of computer vision, they still lack interpretability and are usually designed manually in a cumbersome trial-and-error process. This paper aims at overcoming those limitations by proposing a deep neural network...
Saved in:
| Published in: | arXiv.org 2019-12 |
|---|---|
| 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 | Bastidas Rodriguez, Maria Ximena Gruson, Adrien Polania, Luisa F Shin Fujieda Flavio Prieto Ortiz Takayama, Kohei Hachisuka, Toshiya |
| description | Even though convolutional neural networks have become the method of choice in many fields of computer vision, they still lack interpretability and are usually designed manually in a cumbersome trial-and-error process. This paper aims at overcoming those limitations by proposing a deep neural network, which is designed in a systematic fashion and is interpretable, by integrating multiresolution analysis at the core of the deep neural network design. By using the lifting scheme, it is possible to generate a wavelet representation and design a network capable of learning wavelet coefficients in an end-to-end form. Compared to state-of-the-art architectures, the proposed model requires less hyper-parameter tuning and achieves competitive accuracy in image classification tasks |
| format | article |
| fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2325124005</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2325124005</sourcerecordid><originalsourceid>FETCH-proquest_journals_23251240053</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSQdUlNLVBwTEksKMksS1UITyxLzUktUfBLLSnPL8rmYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8Vn5pUV5QKl4I2MjU0MjEwMDU2PiVAEAPY4roA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2325124005</pqid></control><display><type>article</type><title>Deep Adaptive Wavelet Network</title><source>Publicly Available Content (ProQuest)</source><creator>Bastidas Rodriguez, Maria Ximena ; Gruson, Adrien ; Polania, Luisa F ; Shin Fujieda ; Flavio Prieto Ortiz ; Takayama, Kohei ; Hachisuka, Toshiya</creator><creatorcontrib>Bastidas Rodriguez, Maria Ximena ; Gruson, Adrien ; Polania, Luisa F ; Shin Fujieda ; Flavio Prieto Ortiz ; Takayama, Kohei ; Hachisuka, Toshiya</creatorcontrib><description>Even though convolutional neural networks have become the method of choice in many fields of computer vision, they still lack interpretability and are usually designed manually in a cumbersome trial-and-error process. This paper aims at overcoming those limitations by proposing a deep neural network, which is designed in a systematic fashion and is interpretable, by integrating multiresolution analysis at the core of the deep neural network design. By using the lifting scheme, it is possible to generate a wavelet representation and design a network capable of learning wavelet coefficients in an end-to-end form. Compared to state-of-the-art architectures, the proposed model requires less hyper-parameter tuning and achieves competitive accuracy in image classification tasks</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial neural networks ; Computer vision ; Design ; Image classification ; Multiresolution analysis ; Neural networks ; Wavelet analysis</subject><ispartof>arXiv.org, 2019-12</ispartof><rights>2019. 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/2325124005?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Bastidas Rodriguez, Maria Ximena</creatorcontrib><creatorcontrib>Gruson, Adrien</creatorcontrib><creatorcontrib>Polania, Luisa F</creatorcontrib><creatorcontrib>Shin Fujieda</creatorcontrib><creatorcontrib>Flavio Prieto Ortiz</creatorcontrib><creatorcontrib>Takayama, Kohei</creatorcontrib><creatorcontrib>Hachisuka, Toshiya</creatorcontrib><title>Deep Adaptive Wavelet Network</title><title>arXiv.org</title><description>Even though convolutional neural networks have become the method of choice in many fields of computer vision, they still lack interpretability and are usually designed manually in a cumbersome trial-and-error process. This paper aims at overcoming those limitations by proposing a deep neural network, which is designed in a systematic fashion and is interpretable, by integrating multiresolution analysis at the core of the deep neural network design. By using the lifting scheme, it is possible to generate a wavelet representation and design a network capable of learning wavelet coefficients in an end-to-end form. Compared to state-of-the-art architectures, the proposed model requires less hyper-parameter tuning and achieves competitive accuracy in image classification tasks</description><subject>Artificial neural networks</subject><subject>Computer vision</subject><subject>Design</subject><subject>Image classification</subject><subject>Multiresolution analysis</subject><subject>Neural networks</subject><subject>Wavelet analysis</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSQdUlNLVBwTEksKMksS1UITyxLzUktUfBLLSnPL8rmYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8Vn5pUV5QKl4I2MjU0MjEwMDU2PiVAEAPY4roA</recordid><startdate>20191210</startdate><enddate>20191210</enddate><creator>Bastidas Rodriguez, Maria Ximena</creator><creator>Gruson, Adrien</creator><creator>Polania, Luisa F</creator><creator>Shin Fujieda</creator><creator>Flavio Prieto Ortiz</creator><creator>Takayama, Kohei</creator><creator>Hachisuka, Toshiya</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>20191210</creationdate><title>Deep Adaptive Wavelet Network</title><author>Bastidas Rodriguez, Maria Ximena ; Gruson, Adrien ; Polania, Luisa F ; Shin Fujieda ; Flavio Prieto Ortiz ; Takayama, Kohei ; Hachisuka, Toshiya</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_23251240053</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Artificial neural networks</topic><topic>Computer vision</topic><topic>Design</topic><topic>Image classification</topic><topic>Multiresolution analysis</topic><topic>Neural networks</topic><topic>Wavelet analysis</topic><toplevel>online_resources</toplevel><creatorcontrib>Bastidas Rodriguez, Maria Ximena</creatorcontrib><creatorcontrib>Gruson, Adrien</creatorcontrib><creatorcontrib>Polania, Luisa F</creatorcontrib><creatorcontrib>Shin Fujieda</creatorcontrib><creatorcontrib>Flavio Prieto Ortiz</creatorcontrib><creatorcontrib>Takayama, Kohei</creatorcontrib><creatorcontrib>Hachisuka, Toshiya</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</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: 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>Bastidas Rodriguez, Maria Ximena</au><au>Gruson, Adrien</au><au>Polania, Luisa F</au><au>Shin Fujieda</au><au>Flavio Prieto Ortiz</au><au>Takayama, Kohei</au><au>Hachisuka, Toshiya</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Deep Adaptive Wavelet Network</atitle><jtitle>arXiv.org</jtitle><date>2019-12-10</date><risdate>2019</risdate><eissn>2331-8422</eissn><abstract>Even though convolutional neural networks have become the method of choice in many fields of computer vision, they still lack interpretability and are usually designed manually in a cumbersome trial-and-error process. This paper aims at overcoming those limitations by proposing a deep neural network, which is designed in a systematic fashion and is interpretable, by integrating multiresolution analysis at the core of the deep neural network design. By using the lifting scheme, it is possible to generate a wavelet representation and design a network capable of learning wavelet coefficients in an end-to-end form. Compared to state-of-the-art architectures, the proposed model requires less hyper-parameter tuning and achieves competitive accuracy in image classification tasks</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, 2019-12 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_proquest_journals_2325124005 |
| source | Publicly Available Content (ProQuest) |
| subjects | Artificial neural networks Computer vision Design Image classification Multiresolution analysis Neural networks Wavelet analysis |
| title | Deep Adaptive Wavelet Network |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T01%3A15%3A08IST&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=Deep%20Adaptive%20Wavelet%20Network&rft.jtitle=arXiv.org&rft.au=Bastidas%20Rodriguez,%20Maria%20Ximena&rft.date=2019-12-10&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2325124005%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_23251240053%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2325124005&rft_id=info:pmid/&rfr_iscdi=true |