TauPad: Test Data Augmentation of Point Clouds by Adversarial Mutation

Point clouds have been widely used in a large number of application scenarios to handle with various deep learning (DL) tasks. Testing is an essential means to guarantee the robustness of DL models, which places high demands on test data. Therefore, it is crucial to design a reliable and effective t...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2022 IEEE/ACM 44th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) s. 212 - 216
Hlavní autoři: Liu, Guandi, Liu, Jiawei, Zhang, Quanjun, Fang, Chunrong, Zhang, Xufan
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.05.2022
Témata:
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Point clouds have been widely used in a large number of application scenarios to handle with various deep learning (DL) tasks. Testing is an essential means to guarantee the robustness of DL models, which places high demands on test data. Therefore, it is crucial to design a reliable and effective test data augmentation tool of point clouds to generate high-quality data to test the robustness of the target model. However, although common mutation methods can increase the amount of point clouds, the quality of the augmented data still needs to be improved based on the specify of the spatial structure of the point clouds. In this paper, we develop a point clouds augmentation tool, namely TauPad, of which the specific mutation direction is guided by adversarial attacks. Based on the point clouds pre-processing, point clouds adversarial mutation, and spatial distribution restoration, TauPad can generate augmented test data that are significantly deceptive to the target model. Preliminary experiments show that TauPad can reliably and effectively augment point clouds for testing. Its video is at https://youtu.be/Y9nDIEW13_g/ and TauPad can be used at http://1.13.193.98:2600/.
AbstractList Point clouds have been widely used in a large number of application scenarios to handle with various deep learning (DL) tasks. Testing is an essential means to guarantee the robustness of DL models, which places high demands on test data. Therefore, it is crucial to design a reliable and effective test data augmentation tool of point clouds to generate high-quality data to test the robustness of the target model. However, although common mutation methods can increase the amount of point clouds, the quality of the augmented data still needs to be improved based on the specify of the spatial structure of the point clouds. In this paper, we develop a point clouds augmentation tool, namely TauPad, of which the specific mutation direction is guided by adversarial attacks. Based on the point clouds pre-processing, point clouds adversarial mutation, and spatial distribution restoration, TauPad can generate augmented test data that are significantly deceptive to the target model. Preliminary experiments show that TauPad can reliably and effectively augment point clouds for testing. Its video is at https://youtu.be/Y9nDIEW13_g/ and TauPad can be used at http://1.13.193.98:2600/.
Author Liu, Guandi
Zhang, Xufan
Zhang, Quanjun
Fang, Chunrong
Liu, Jiawei
Author_xml – sequence: 1
  givenname: Guandi
  surname: Liu
  fullname: Liu, Guandi
  organization: Nanjing University,State Key Laboratory for Novel Software Technology,China
– sequence: 2
  givenname: Jiawei
  surname: Liu
  fullname: Liu, Jiawei
  organization: Nanjing University,State Key Laboratory for Novel Software Technology,China
– sequence: 3
  givenname: Quanjun
  surname: Zhang
  fullname: Zhang, Quanjun
  organization: Nanjing University,State Key Laboratory for Novel Software Technology,China
– sequence: 4
  givenname: Chunrong
  surname: Fang
  fullname: Fang, Chunrong
  email: fangchunrong@nju.edu.cn
  organization: Nanjing University,State Key Laboratory for Novel Software Technology,China
– sequence: 5
  givenname: Xufan
  surname: Zhang
  fullname: Zhang, Xufan
  organization: Nanjing University,State Key Laboratory for Novel Software Technology,China
BookMark eNotzLFOwzAQgGEjwQClMwOLXyDFzp1jmy0KtCAV0SHM1aU-o0hpghIHqW9PpTL9y6f_Tlz3Q89CPGi10hrNExit0ODqXKuMuhJLb50uCoPeeKdvxbqmeUfhWdY8JflCiWQ5fx-5T5TaoZdDlLuh7ZOsumEOk2xOsgy_PE40ttTJj_ni7sVNpG7i5X8X4mv9Wldv2fZz816V24y0tSlDR5grlaNV3moIJkaI0HB0EKxjaNxBkdI5MQI5IoVgDxxtLDyfoYaFeLx8W2be_4ztkcbT3lsPFhH-AJU9R2E
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1145/3510454.3517050
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781665495981
1665495987
EndPage 216
ExternalDocumentID 9793744
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  funderid: 10.13039/501100001809
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-a177t-48a420024709713d5ff3f3bef83d78e3b8c0a012ae43a8aa0437cef7f69e3f313
IEDL.DBID RIE
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000850203800044&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Thu Jan 18 11:13:20 EST 2024
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a177t-48a420024709713d5ff3f3bef83d78e3b8c0a012ae43a8aa0437cef7f69e3f313
PageCount 5
ParticipantIDs ieee_primary_9793744
PublicationCentury 2000
PublicationDate 2022-May
PublicationDateYYYYMMDD 2022-05-01
PublicationDate_xml – month: 05
  year: 2022
  text: 2022-May
PublicationDecade 2020
PublicationTitle 2022 IEEE/ACM 44th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion)
PublicationTitleAbbrev ICSE-COMPANION
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.8027241
Snippet Point clouds have been widely used in a large number of application scenarios to handle with various deep learning (DL) tasks. Testing is an essential means to...
SourceID ieee
SourceType Publisher
StartPage 212
SubjectTerms Data models
Manuals
Measurement
Point cloud compression
Reliability engineering
Robustness
Software and its engineering → Software testing and debugging
Software testing
Title TauPad: Test Data Augmentation of Point Clouds by Adversarial Mutation
URI https://ieeexplore.ieee.org/document/9793744
WOSCitedRecordID wos000850203800044&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA5zePCksom_ycGj3dombRJvMh1eHD1M2G28Ji8y0Fa2VvC_N8nK9ODFU0J4EJI88vLjfd9HyI1MGcZgRaQhwYhnNo0UuluKSqQ1zLhDvi2D2ISYzeRioYoeud1hYRAxJJ_hyFfDX76pdeufysbKk7lxvkf2hMi3WK2OrSfh2Zg59-IZH7lSxB5H_0suJUSL6eH_-jkiwx_YHS12AeWY9LAakOkc2gLMHZ27_Zs-QAP0vn197yBDFa0tLepV1dDJW92aDS2_aBBZ3oB3Lfrcbu2G5GX6OJ88RZ34QQSJEE3EJXCfQMGFZ3liJrOWWVailcwIiayUOgYXXQA5AwngOYo0WmFzhc4wYSekX9UVnhJaKpvHyCTk7vKQigw0T6xSHLTMrCzlGRn4OVh-bPktlt3wz_9uviAHqYcAhKS_S9Jv1i1ekX392aw26-uwKN_IkI-M
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA5zCnpS2cTf5uDRbm2TLIk3UcfEbfRQYbfx2r7IQFvZWsH_3qQr04MXTwnhQUjyyMuP930fIdcqZOiDkV4KAXpcmNDTaG8pOlAmY5k95JukFpuQ06mazXTUIjcbLAwi1sln2HPV-i8_K9LKPZX1tSNz43yLbAvOQ3-N1mr4egIu-sw6GBe8Z0vpOyT9L8GUOl4M9__X0wHp_gDvaLQJKYekhXmHDGOoIshuaWx3cPoAJdC76vW9AQ3ltDA0KhZ5Se_fiipb0eSL1jLLK3DORSfV2q5LXoaP8f3Ia-QPPAikLD2ugLsUCi4dzxPLhDHMsASNYplUyBKV-mDjCyBnoAAcS1GKRpqBRmsYsCPSzoscjwlNtBn4yBQM7PUhlAJSHhitOaRKGJWoE9JxczD_WDNczJvhn_7dfEV2R_FkPB8_TZ_PyF7oAAF1CuA5aZfLCi_ITvpZLlbLy3qBvgFxfZLT
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2022+IEEE%2FACM+44th+International+Conference+on+Software+Engineering%3A+Companion+Proceedings+%28ICSE-Companion%29&rft.atitle=TauPad%3A+Test+Data+Augmentation+of+Point+Clouds+by+Adversarial+Mutation&rft.au=Liu%2C+Guandi&rft.au=Liu%2C+Jiawei&rft.au=Zhang%2C+Quanjun&rft.au=Fang%2C+Chunrong&rft.date=2022-05-01&rft.pub=IEEE&rft.spage=212&rft.epage=216&rft_id=info:doi/10.1145%2F3510454.3517050&rft.externalDocID=9793744