Augmenting Anchors by the Detector Itself
Usually, it is difficult to determine the scale and aspect ratio of anchors for anchor-based object detection methods. Current state-of-the-art object detectors either determine anchor parameters according to objects' shape and scale in a dataset, or avoid this problem by utilizing anchor-free...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2022-04 |
---|---|
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 | Wan, Xiaopei Li, Guoqiu Yang, Yujiu Guo, Zhenhua |
description | Usually, it is difficult to determine the scale and aspect ratio of anchors for anchor-based object detection methods. Current state-of-the-art object detectors either determine anchor parameters according to objects' shape and scale in a dataset, or avoid this problem by utilizing anchor-free methods, however, the former scheme is dataset-specific and the latter methods could not get better performance than the former ones. In this paper, we propose a novel anchor augmentation method named AADI, which means Augmenting Anchors by the Detector Itself. AADI is not an anchor-free method, instead, it can convert the scale and aspect ratio of anchors from a continuous space to a discrete space, which greatly alleviates the problem of anchors' designation. Furthermore, AADI is a learning-based anchor augmentation method, but it does not add any parameters or hyper-parameters, which is beneficial for research and downstream tasks. Extensive experiments on COCO dataset demonstrate the effectiveness of AADI, specifically, AADI achieves significant performance boosts on many state-of-the-art object detectors (eg. at least +2.4 box AP on Faster R-CNN, +2.2 box AP on Mask R-CNN, and +0.9 box AP on Cascade Mask R-CNN). We hope that this simple and cost-efficient method can be widely used in object detection. Code and models are available at https://github.com/WanXiaopei/aadi. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2535631196</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2535631196</sourcerecordid><originalsourceid>FETCH-proquest_journals_25356311963</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQdCxNz03NK8nMS1dwzEvOyC8qVkiqVCjJSFVwSS1JTS7JL1LwLClOzUnjYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8Vn5pUV5QKl4I1NjUzNjQ0NLM2PiVAEAwhYwOg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2535631196</pqid></control><display><type>article</type><title>Augmenting Anchors by the Detector Itself</title><source>Freely Accessible Journals</source><creator>Wan, Xiaopei ; Li, Guoqiu ; Yang, Yujiu ; Guo, Zhenhua</creator><creatorcontrib>Wan, Xiaopei ; Li, Guoqiu ; Yang, Yujiu ; Guo, Zhenhua</creatorcontrib><description>Usually, it is difficult to determine the scale and aspect ratio of anchors for anchor-based object detection methods. Current state-of-the-art object detectors either determine anchor parameters according to objects' shape and scale in a dataset, or avoid this problem by utilizing anchor-free methods, however, the former scheme is dataset-specific and the latter methods could not get better performance than the former ones. In this paper, we propose a novel anchor augmentation method named AADI, which means Augmenting Anchors by the Detector Itself. AADI is not an anchor-free method, instead, it can convert the scale and aspect ratio of anchors from a continuous space to a discrete space, which greatly alleviates the problem of anchors' designation. Furthermore, AADI is a learning-based anchor augmentation method, but it does not add any parameters or hyper-parameters, which is beneficial for research and downstream tasks. Extensive experiments on COCO dataset demonstrate the effectiveness of AADI, specifically, AADI achieves significant performance boosts on many state-of-the-art object detectors (eg. at least +2.4 box AP on Faster R-CNN, +2.2 box AP on Mask R-CNN, and +0.9 box AP on Cascade Mask R-CNN). We hope that this simple and cost-efficient method can be widely used in object detection. Code and models are available at https://github.com/WanXiaopei/aadi.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Aspect ratio ; Datasets ; Object recognition ; Parameters ; Scale (ratio)</subject><ispartof>arXiv.org, 2022-04</ispartof><rights>2022. This work is published under http://creativecommons.org/licenses/by-nc-sa/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><link.rule.ids>781,785</link.rule.ids></links><search><creatorcontrib>Wan, Xiaopei</creatorcontrib><creatorcontrib>Li, Guoqiu</creatorcontrib><creatorcontrib>Yang, Yujiu</creatorcontrib><creatorcontrib>Guo, Zhenhua</creatorcontrib><title>Augmenting Anchors by the Detector Itself</title><title>arXiv.org</title><description>Usually, it is difficult to determine the scale and aspect ratio of anchors for anchor-based object detection methods. Current state-of-the-art object detectors either determine anchor parameters according to objects' shape and scale in a dataset, or avoid this problem by utilizing anchor-free methods, however, the former scheme is dataset-specific and the latter methods could not get better performance than the former ones. In this paper, we propose a novel anchor augmentation method named AADI, which means Augmenting Anchors by the Detector Itself. AADI is not an anchor-free method, instead, it can convert the scale and aspect ratio of anchors from a continuous space to a discrete space, which greatly alleviates the problem of anchors' designation. Furthermore, AADI is a learning-based anchor augmentation method, but it does not add any parameters or hyper-parameters, which is beneficial for research and downstream tasks. Extensive experiments on COCO dataset demonstrate the effectiveness of AADI, specifically, AADI achieves significant performance boosts on many state-of-the-art object detectors (eg. at least +2.4 box AP on Faster R-CNN, +2.2 box AP on Mask R-CNN, and +0.9 box AP on Cascade Mask R-CNN). We hope that this simple and cost-efficient method can be widely used in object detection. Code and models are available at https://github.com/WanXiaopei/aadi.</description><subject>Aspect ratio</subject><subject>Datasets</subject><subject>Object recognition</subject><subject>Parameters</subject><subject>Scale (ratio)</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQdCxNz03NK8nMS1dwzEvOyC8qVkiqVCjJSFVwSS1JTS7JL1LwLClOzUnjYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8Vn5pUV5QKl4I1NjUzNjQ0NLM2PiVAEAwhYwOg</recordid><startdate>20220427</startdate><enddate>20220427</enddate><creator>Wan, Xiaopei</creator><creator>Li, Guoqiu</creator><creator>Yang, Yujiu</creator><creator>Guo, Zhenhua</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>20220427</creationdate><title>Augmenting Anchors by the Detector Itself</title><author>Wan, Xiaopei ; Li, Guoqiu ; Yang, Yujiu ; Guo, Zhenhua</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_25356311963</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Aspect ratio</topic><topic>Datasets</topic><topic>Object recognition</topic><topic>Parameters</topic><topic>Scale (ratio)</topic><toplevel>online_resources</toplevel><creatorcontrib>Wan, Xiaopei</creatorcontrib><creatorcontrib>Li, Guoqiu</creatorcontrib><creatorcontrib>Yang, Yujiu</creatorcontrib><creatorcontrib>Guo, Zhenhua</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>Access via ProQuest (Open Access)</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>Wan, Xiaopei</au><au>Li, Guoqiu</au><au>Yang, Yujiu</au><au>Guo, Zhenhua</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Augmenting Anchors by the Detector Itself</atitle><jtitle>arXiv.org</jtitle><date>2022-04-27</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Usually, it is difficult to determine the scale and aspect ratio of anchors for anchor-based object detection methods. Current state-of-the-art object detectors either determine anchor parameters according to objects' shape and scale in a dataset, or avoid this problem by utilizing anchor-free methods, however, the former scheme is dataset-specific and the latter methods could not get better performance than the former ones. In this paper, we propose a novel anchor augmentation method named AADI, which means Augmenting Anchors by the Detector Itself. AADI is not an anchor-free method, instead, it can convert the scale and aspect ratio of anchors from a continuous space to a discrete space, which greatly alleviates the problem of anchors' designation. Furthermore, AADI is a learning-based anchor augmentation method, but it does not add any parameters or hyper-parameters, which is beneficial for research and downstream tasks. Extensive experiments on COCO dataset demonstrate the effectiveness of AADI, specifically, AADI achieves significant performance boosts on many state-of-the-art object detectors (eg. at least +2.4 box AP on Faster R-CNN, +2.2 box AP on Mask R-CNN, and +0.9 box AP on Cascade Mask R-CNN). We hope that this simple and cost-efficient method can be widely used in object detection. Code and models are available at https://github.com/WanXiaopei/aadi.</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, 2022-04 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2535631196 |
source | Freely Accessible Journals |
subjects | Aspect ratio Datasets Object recognition Parameters Scale (ratio) |
title | Augmenting Anchors by the Detector Itself |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-14T16%3A39%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=Augmenting%20Anchors%20by%20the%20Detector%20Itself&rft.jtitle=arXiv.org&rft.au=Wan,%20Xiaopei&rft.date=2022-04-27&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2535631196%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2535631196&rft_id=info:pmid/&rfr_iscdi=true |