Rewrite the Stars

Recent studies have drawn attention to the untapped potential of the "star operation" (element-wise multiplication) in network design. While intuitive explanations abound, the foundational rationale behind its application remains largely unexplored. Our study attempts to reveal the star op...

Full description

Saved in:
Bibliographic Details
Published inProceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 5694 - 5703
Main Authors Ma, Xu, Dai, Xiyang, Bai, Yue, Wang, Yizhou, Fu, Yun
Format Conference Proceeding
LanguageEnglish
Published IEEE 16.06.2024
Subjects
Online AccessGet full text
ISSN1063-6919
DOI10.1109/CVPR52733.2024.00544

Cover

Loading…
Abstract Recent studies have drawn attention to the untapped potential of the "star operation" (element-wise multiplication) in network design. While intuitive explanations abound, the foundational rationale behind its application remains largely unexplored. Our study attempts to reveal the star operation's ability of mapping inputs into high-dimensional, non-linear feature spaces-akin to kernel tricks-without widening the network. We further introduce StarNet, a simple yet pow-erful prototype, demonstrating impressive performance and low latency under compact network structure and efficient budget. Like stars in the sky, the star operation appears unremarkable but holds a vast universe of potential. Our work encourages further exploration across tasks, with codes available at https://github.com/ma-xu/Rewrite-the-Stars.
AbstractList Recent studies have drawn attention to the untapped potential of the "star operation" (element-wise multiplication) in network design. While intuitive explanations abound, the foundational rationale behind its application remains largely unexplored. Our study attempts to reveal the star operation's ability of mapping inputs into high-dimensional, non-linear feature spaces-akin to kernel tricks-without widening the network. We further introduce StarNet, a simple yet pow-erful prototype, demonstrating impressive performance and low latency under compact network structure and efficient budget. Like stars in the sky, the star operation appears unremarkable but holds a vast universe of potential. Our work encourages further exploration across tasks, with codes available at https://github.com/ma-xu/Rewrite-the-Stars.
Author Dai, Xiyang
Fu, Yun
Bai, Yue
Wang, Yizhou
Ma, Xu
Author_xml – sequence: 1
  givenname: Xu
  surname: Ma
  fullname: Ma, Xu
  organization: Northeastern University
– sequence: 2
  givenname: Xiyang
  surname: Dai
  fullname: Dai, Xiyang
  organization: Microsoft
– sequence: 3
  givenname: Yue
  surname: Bai
  fullname: Bai, Yue
  organization: Northeastern University
– sequence: 4
  givenname: Yizhou
  surname: Wang
  fullname: Wang, Yizhou
  organization: Northeastern University
– sequence: 5
  givenname: Yun
  surname: Fu
  fullname: Fu, Yun
  organization: Northeastern University
BookMark eNotjstKA0EQAFuJYBL34D2H_MBuuqfn0XOUxUcgEInRa5hhZnBFo-wuiH9vQKlD3YqaweT4ecwAC8KGCP2qfXncGeWYG4VKN4hG6zOovPPCBtkwoj2HKaHl2nryl1ANwxsisiKyXqZwvcvffTfm5fial09j6IcruCjhfcjVv-fwfHe7bx_qzfZ-3d5s6o6cHeuggyqYVMLoJJJRJ9hzFOOVipKMDUFKiSJUCCM5IXbRJY-UYnCG57D463Y558NX332E_udwWjVWs-ZfJHI6eQ
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR52733.2024.00544
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 9798350353006
EISSN 1063-6919
EndPage 5703
ExternalDocumentID 10656434
Genre orig-research
GroupedDBID 6IE
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i176t-a4a2f0d2d0b78b152525393b85922b8d56aa8ffb881f10b178137b7d901dba753
IEDL.DBID RIE
IngestDate Wed Aug 27 02:00:49 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i176t-a4a2f0d2d0b78b152525393b85922b8d56aa8ffb881f10b178137b7d901dba753
PageCount 10
ParticipantIDs ieee_primary_10656434
PublicationCentury 2000
PublicationDate 2024-June-16
PublicationDateYYYYMMDD 2024-06-16
PublicationDate_xml – month: 06
  year: 2024
  text: 2024-June-16
  day: 16
PublicationDecade 2020
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
Score 2.654302
Snippet Recent studies have drawn attention to the untapped potential of the "star operation" (element-wise multiplication) in network design. While intuitive...
SourceID ieee
SourceType Publisher
StartPage 5694
SubjectTerms Computer vision
element-wise multiplication
Pattern recognition
Polynomials
Prototypes
rewrite the stars
Solids
StarNet
Stars
Visualization
Title Rewrite the Stars
URI https://ieeexplore.ieee.org/document/10656434
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LSwMxEB5sT55ateKbPXjdunluci6WIlhKsdJbSTYJiNBKu6Xgr3eyu60oCN5CLnkxzPdN5psBuFeBe1kwkiqbx9ANN6kVxKfe82C404qyKE5-HsvRjD_NxbwRq1daGO99lXzm-3FY_eW7VbGNoTK0cEQfnPEWtJC51WKtQ0CFIZWRWjXyOJLph8HrZBrrizGkgTQWyRac_2iiUvmQYQfG-9Xr1JH3_ra0_eLzV2HGf2-vC71vuV4yOTiiEzjyy1PoNPgyaax3cwbdqd-tEWImCPoSRJnrTQ9mw8eXwShtWiKkbySXZWq4oSFz1GV4tTb2LqKCaWaV0JRa5YQ0RoVglSKBZJbkirDc5g69vrMGqck5tJerpb-AxGRIqhEsCYuPgpasizywII2mzmgrwyX04hEXH3XVi8X-dFd_zF_DcbzmmEZF5A20y_XW36LDLu1d9VBfu3SS9A
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LSwMxEB60HvTUqhXf7sHr1s1zk3OxVG1LKa30VpLdBERopd0i-OudbNeKguAt5JLMhGG-mcw3A3CrPHcyYyRWNg2pG25iK4iLnePe8FwrygI5uT-Q3Ql_nIppRVYvuTDOubL4zLXCsvzLzxfZOqTK0MIRfXDGd2FPBDbuhq61TakwDGakVhVBjiT6rv08HIUOYwwDQRraZAvOf4xRKb1Ipw6Dr_M3xSOvrXVhW9nHr9aM_75gA5rfhL1ouHVFh7Dj5kdQrxBmVNnv6hgaI_e-RJAZIeyLEGcuV02YdO7H7W5cDUWIX0gqi9hwQ32S0zxB5dowvYgKpplVQlNqVS6kMcp7qxTxJLEkVYSlNs3R7-fWYHByArX5Yu5OITIJhtUIl4TFZ0Fb1lnqmZdG09xoK_0ZNIOIs7dN34vZl3Tnf-zfwH533O_Neg-Dpws4CCoPRVVEXkKtWK7dFbrvwl6Xj_YJnTeWPA
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=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=Rewrite+the+Stars&rft.au=Ma%2C+Xu&rft.au=Dai%2C+Xiyang&rft.au=Bai%2C+Yue&rft.au=Wang%2C+Yizhou&rft.date=2024-06-16&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=5694&rft.epage=5703&rft_id=info:doi/10.1109%2FCVPR52733.2024.00544&rft.externalDocID=10656434