Efficient Uncertainty Estimation for Semantic Segmentation in Videos
Uncertainty estimation in deep learning becomes more important recently. A deep learning model can't be applied in real applications if we don't know whether the model is certain about the decision or not. Some literature proposes the Bayesian neural network which can estimate the uncertai...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2018-07 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Po-Yu, Huang Wan-Ting, Hsu Chun-Yueh Chiu Ting-Fan, Wu Sun, Min |
description | Uncertainty estimation in deep learning becomes more important recently. A deep learning model can't be applied in real applications if we don't know whether the model is certain about the decision or not. Some literature proposes the Bayesian neural network which can estimate the uncertainty by Monte Carlo Dropout (MC dropout). However, MC dropout needs to forward the model \(N\) times which results in \(N\) times slower. For real-time applications such as a self-driving car system, which needs to obtain the prediction and the uncertainty as fast as possible, so that MC dropout becomes impractical. In this work, we propose the region-based temporal aggregation (RTA) method which leverages the temporal information in videos to simulate the sampling procedure. Our RTA method with Tiramisu backbone is 10x faster than the MC dropout with Tiramisu backbone (\(N=5\)). Furthermore, the uncertainty estimation obtained by our RTA method is comparable to MC dropout's uncertainty estimation on pixel-level and frame-level metrics. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2092770106</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2092770106</sourcerecordid><originalsourceid>FETCH-proquest_journals_20927701063</originalsourceid><addsrcrecordid>eNqNissKwjAQAIMgWLT_EPBcSDd96Fkr3n1cS6iJbLEbTbYH_96CfoCnGZiZiQS0zrNNAbAQaYy9UgqqGspSJ2LfOIcdWmJ5oc4GNkj8lk1kHAyjJ-l8kCc7GGLsJrkP0_stSPKKN-vjSsydeUSb_rgU60Nz3h2zZ_Cv0UZuez8GmlILagt1rXJV6f-uD2wAOtc</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2092770106</pqid></control><display><type>article</type><title>Efficient Uncertainty Estimation for Semantic Segmentation in Videos</title><source>Free E- Journals</source><creator>Po-Yu, Huang ; Wan-Ting, Hsu ; Chun-Yueh Chiu ; Ting-Fan, Wu ; Sun, Min</creator><creatorcontrib>Po-Yu, Huang ; Wan-Ting, Hsu ; Chun-Yueh Chiu ; Ting-Fan, Wu ; Sun, Min</creatorcontrib><description>Uncertainty estimation in deep learning becomes more important recently. A deep learning model can't be applied in real applications if we don't know whether the model is certain about the decision or not. Some literature proposes the Bayesian neural network which can estimate the uncertainty by Monte Carlo Dropout (MC dropout). However, MC dropout needs to forward the model \(N\) times which results in \(N\) times slower. For real-time applications such as a self-driving car system, which needs to obtain the prediction and the uncertainty as fast as possible, so that MC dropout becomes impractical. In this work, we propose the region-based temporal aggregation (RTA) method which leverages the temporal information in videos to simulate the sampling procedure. Our RTA method with Tiramisu backbone is 10x faster than the MC dropout with Tiramisu backbone (\(N=5\)). Furthermore, the uncertainty estimation obtained by our RTA method is comparable to MC dropout's uncertainty estimation on pixel-level and frame-level metrics.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Autonomous cars ; Backbone ; Bayesian analysis ; Computer simulation ; Machine learning ; Neural networks ; Semantic segmentation ; Uncertainty</subject><ispartof>arXiv.org, 2018-07</ispartof><rights>2018. 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><link.rule.ids>781,785</link.rule.ids></links><search><creatorcontrib>Po-Yu, Huang</creatorcontrib><creatorcontrib>Wan-Ting, Hsu</creatorcontrib><creatorcontrib>Chun-Yueh Chiu</creatorcontrib><creatorcontrib>Ting-Fan, Wu</creatorcontrib><creatorcontrib>Sun, Min</creatorcontrib><title>Efficient Uncertainty Estimation for Semantic Segmentation in Videos</title><title>arXiv.org</title><description>Uncertainty estimation in deep learning becomes more important recently. A deep learning model can't be applied in real applications if we don't know whether the model is certain about the decision or not. Some literature proposes the Bayesian neural network which can estimate the uncertainty by Monte Carlo Dropout (MC dropout). However, MC dropout needs to forward the model \(N\) times which results in \(N\) times slower. For real-time applications such as a self-driving car system, which needs to obtain the prediction and the uncertainty as fast as possible, so that MC dropout becomes impractical. In this work, we propose the region-based temporal aggregation (RTA) method which leverages the temporal information in videos to simulate the sampling procedure. Our RTA method with Tiramisu backbone is 10x faster than the MC dropout with Tiramisu backbone (\(N=5\)). Furthermore, the uncertainty estimation obtained by our RTA method is comparable to MC dropout's uncertainty estimation on pixel-level and frame-level metrics.</description><subject>Autonomous cars</subject><subject>Backbone</subject><subject>Bayesian analysis</subject><subject>Computer simulation</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Semantic segmentation</subject><subject>Uncertainty</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNissKwjAQAIMgWLT_EPBcSDd96Fkr3n1cS6iJbLEbTbYH_96CfoCnGZiZiQS0zrNNAbAQaYy9UgqqGspSJ2LfOIcdWmJ5oc4GNkj8lk1kHAyjJ-l8kCc7GGLsJrkP0_stSPKKN-vjSsydeUSb_rgU60Nz3h2zZ_Cv0UZuez8GmlILagt1rXJV6f-uD2wAOtc</recordid><startdate>20180729</startdate><enddate>20180729</enddate><creator>Po-Yu, Huang</creator><creator>Wan-Ting, Hsu</creator><creator>Chun-Yueh Chiu</creator><creator>Ting-Fan, Wu</creator><creator>Sun, Min</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>20180729</creationdate><title>Efficient Uncertainty Estimation for Semantic Segmentation in Videos</title><author>Po-Yu, Huang ; Wan-Ting, Hsu ; Chun-Yueh Chiu ; Ting-Fan, Wu ; Sun, Min</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_20927701063</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Autonomous cars</topic><topic>Backbone</topic><topic>Bayesian analysis</topic><topic>Computer simulation</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Semantic segmentation</topic><topic>Uncertainty</topic><toplevel>online_resources</toplevel><creatorcontrib>Po-Yu, Huang</creatorcontrib><creatorcontrib>Wan-Ting, Hsu</creatorcontrib><creatorcontrib>Chun-Yueh Chiu</creatorcontrib><creatorcontrib>Ting-Fan, Wu</creatorcontrib><creatorcontrib>Sun, Min</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</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 Korea</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>Po-Yu, Huang</au><au>Wan-Ting, Hsu</au><au>Chun-Yueh Chiu</au><au>Ting-Fan, Wu</au><au>Sun, Min</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Efficient Uncertainty Estimation for Semantic Segmentation in Videos</atitle><jtitle>arXiv.org</jtitle><date>2018-07-29</date><risdate>2018</risdate><eissn>2331-8422</eissn><abstract>Uncertainty estimation in deep learning becomes more important recently. A deep learning model can't be applied in real applications if we don't know whether the model is certain about the decision or not. Some literature proposes the Bayesian neural network which can estimate the uncertainty by Monte Carlo Dropout (MC dropout). However, MC dropout needs to forward the model \(N\) times which results in \(N\) times slower. For real-time applications such as a self-driving car system, which needs to obtain the prediction and the uncertainty as fast as possible, so that MC dropout becomes impractical. In this work, we propose the region-based temporal aggregation (RTA) method which leverages the temporal information in videos to simulate the sampling procedure. Our RTA method with Tiramisu backbone is 10x faster than the MC dropout with Tiramisu backbone (\(N=5\)). Furthermore, the uncertainty estimation obtained by our RTA method is comparable to MC dropout's uncertainty estimation on pixel-level and frame-level metrics.</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, 2018-07 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2092770106 |
source | Free E- Journals |
subjects | Autonomous cars Backbone Bayesian analysis Computer simulation Machine learning Neural networks Semantic segmentation Uncertainty |
title | Efficient Uncertainty Estimation for Semantic Segmentation in Videos |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-18T11%3A12%3A58IST&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=Efficient%20Uncertainty%20Estimation%20for%20Semantic%20Segmentation%20in%20Videos&rft.jtitle=arXiv.org&rft.au=Po-Yu,%20Huang&rft.date=2018-07-29&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2092770106%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2092770106&rft_id=info:pmid/&rfr_iscdi=true |