Knowledge Distillation for End-to-End Person Search

We introduce knowledge distillation for end-to-end person search. End-to-End methods are the current state-of-the-art for person search that solve both detection and re-identification jointly. These approaches for joint optimization show their largest drop in performance due to a sub-optimal detecto...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Munjal, Bharti, Galasso, Fabio, Amin, Sikandar
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Munjal, Bharti
Galasso, Fabio
Amin, Sikandar
description We introduce knowledge distillation for end-to-end person search. End-to-End methods are the current state-of-the-art for person search that solve both detection and re-identification jointly. These approaches for joint optimization show their largest drop in performance due to a sub-optimal detector. We propose two distinct approaches for extra supervision of end-to-end person search methods in a teacher-student setting. The first is adopted from state-of-the-art knowledge distillation in object detection. We employ this to supervise the detector of our person search model at various levels using a specialized detector. The second approach is new, simple and yet considerably more effective. This distills knowledge from a teacher re-identification technique via a pre-computed look-up table of ID features. It relaxes the learning of identification features and allows the student to focus on the detection task. This procedure not only helps fixing the sub-optimal detector training in the joint optimization and simultaneously improving the person search, but also closes the performance gap between the teacher and the student for model compression in this case. Overall, we demonstrate significant improvements for two recent state-of-the-art methods using our proposed knowledge distillation approach on two benchmark datasets. Moreover, on the model compression task our approach brings the performance of smaller models on par with the larger models.
doi_str_mv 10.48550/arxiv.1909.01058
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1909_01058</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1909_01058</sourcerecordid><originalsourceid>FETCH-LOGICAL-a678-bf01948128e6797aa6fc401578429947d8cbfd3b2735a97d0250b616783c34153</originalsourceid><addsrcrecordid>eNotjsGKwjAURbNxITof4Mr-QOpLkzTJUhxnlBEUdF9em0QDtR3S4sz8vdVxdeDCPRxCZgxSoaWEBcbfcEuZAZMCA6nHhH817U_t7Nkl76HrQ11jH9om8W1M1o2lfUsHJAcXu2E9OozVZUpGHuvOvb04IaeP9Wm1obv953a13FHMlaalB2aEZpl2uTIKMfeVACaVFpkxQlldld7yMlNcolEWMgllzoYrr7hgkk_I_F_7rC6-Y7hi_Cse9cWznt8Bf0I9Mw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Knowledge Distillation for End-to-End Person Search</title><source>arXiv.org</source><creator>Munjal, Bharti ; Galasso, Fabio ; Amin, Sikandar</creator><creatorcontrib>Munjal, Bharti ; Galasso, Fabio ; Amin, Sikandar</creatorcontrib><description>We introduce knowledge distillation for end-to-end person search. End-to-End methods are the current state-of-the-art for person search that solve both detection and re-identification jointly. These approaches for joint optimization show their largest drop in performance due to a sub-optimal detector. We propose two distinct approaches for extra supervision of end-to-end person search methods in a teacher-student setting. The first is adopted from state-of-the-art knowledge distillation in object detection. We employ this to supervise the detector of our person search model at various levels using a specialized detector. The second approach is new, simple and yet considerably more effective. This distills knowledge from a teacher re-identification technique via a pre-computed look-up table of ID features. It relaxes the learning of identification features and allows the student to focus on the detection task. This procedure not only helps fixing the sub-optimal detector training in the joint optimization and simultaneously improving the person search, but also closes the performance gap between the teacher and the student for model compression in this case. Overall, we demonstrate significant improvements for two recent state-of-the-art methods using our proposed knowledge distillation approach on two benchmark datasets. Moreover, on the model compression task our approach brings the performance of smaller models on par with the larger models.</description><identifier>DOI: 10.48550/arxiv.1909.01058</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2019-09</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1909.01058$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1909.01058$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Munjal, Bharti</creatorcontrib><creatorcontrib>Galasso, Fabio</creatorcontrib><creatorcontrib>Amin, Sikandar</creatorcontrib><title>Knowledge Distillation for End-to-End Person Search</title><description>We introduce knowledge distillation for end-to-end person search. End-to-End methods are the current state-of-the-art for person search that solve both detection and re-identification jointly. These approaches for joint optimization show their largest drop in performance due to a sub-optimal detector. We propose two distinct approaches for extra supervision of end-to-end person search methods in a teacher-student setting. The first is adopted from state-of-the-art knowledge distillation in object detection. We employ this to supervise the detector of our person search model at various levels using a specialized detector. The second approach is new, simple and yet considerably more effective. This distills knowledge from a teacher re-identification technique via a pre-computed look-up table of ID features. It relaxes the learning of identification features and allows the student to focus on the detection task. This procedure not only helps fixing the sub-optimal detector training in the joint optimization and simultaneously improving the person search, but also closes the performance gap between the teacher and the student for model compression in this case. Overall, we demonstrate significant improvements for two recent state-of-the-art methods using our proposed knowledge distillation approach on two benchmark datasets. Moreover, on the model compression task our approach brings the performance of smaller models on par with the larger models.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotjsGKwjAURbNxITof4Mr-QOpLkzTJUhxnlBEUdF9em0QDtR3S4sz8vdVxdeDCPRxCZgxSoaWEBcbfcEuZAZMCA6nHhH817U_t7Nkl76HrQ11jH9om8W1M1o2lfUsHJAcXu2E9OozVZUpGHuvOvb04IaeP9Wm1obv953a13FHMlaalB2aEZpl2uTIKMfeVACaVFpkxQlldld7yMlNcolEWMgllzoYrr7hgkk_I_F_7rC6-Y7hi_Cse9cWznt8Bf0I9Mw</recordid><startdate>20190903</startdate><enddate>20190903</enddate><creator>Munjal, Bharti</creator><creator>Galasso, Fabio</creator><creator>Amin, Sikandar</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20190903</creationdate><title>Knowledge Distillation for End-to-End Person Search</title><author>Munjal, Bharti ; Galasso, Fabio ; Amin, Sikandar</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a678-bf01948128e6797aa6fc401578429947d8cbfd3b2735a97d0250b616783c34153</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Munjal, Bharti</creatorcontrib><creatorcontrib>Galasso, Fabio</creatorcontrib><creatorcontrib>Amin, Sikandar</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Munjal, Bharti</au><au>Galasso, Fabio</au><au>Amin, Sikandar</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Knowledge Distillation for End-to-End Person Search</atitle><date>2019-09-03</date><risdate>2019</risdate><abstract>We introduce knowledge distillation for end-to-end person search. End-to-End methods are the current state-of-the-art for person search that solve both detection and re-identification jointly. These approaches for joint optimization show their largest drop in performance due to a sub-optimal detector. We propose two distinct approaches for extra supervision of end-to-end person search methods in a teacher-student setting. The first is adopted from state-of-the-art knowledge distillation in object detection. We employ this to supervise the detector of our person search model at various levels using a specialized detector. The second approach is new, simple and yet considerably more effective. This distills knowledge from a teacher re-identification technique via a pre-computed look-up table of ID features. It relaxes the learning of identification features and allows the student to focus on the detection task. This procedure not only helps fixing the sub-optimal detector training in the joint optimization and simultaneously improving the person search, but also closes the performance gap between the teacher and the student for model compression in this case. Overall, we demonstrate significant improvements for two recent state-of-the-art methods using our proposed knowledge distillation approach on two benchmark datasets. Moreover, on the model compression task our approach brings the performance of smaller models on par with the larger models.</abstract><doi>10.48550/arxiv.1909.01058</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1909.01058
ispartof
issn
language eng
recordid cdi_arxiv_primary_1909_01058
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title Knowledge Distillation for End-to-End Person Search
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T11%3A17%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Knowledge%20Distillation%20for%20End-to-End%20Person%20Search&rft.au=Munjal,%20Bharti&rft.date=2019-09-03&rft_id=info:doi/10.48550/arxiv.1909.01058&rft_dat=%3Carxiv_GOX%3E1909_01058%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true