Easz: An Agile Transformer-based Image Compression Framework for Resource-constrained IoTs

Neural image compression, necessary in various machine-to-machine communication scenarios, suffers from its heavy encode-decode structures and inflexibility in switching between different compression levels. Consequently, it raises significant challenges in applying the neural image compression to e...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2025 62nd ACM/IEEE Design Automation Conference (DAC) S. 1 - 7
Hauptverfasser: Mao, Yu, Li, Jingzong, Wang, Jun, Xu, Hong, Kuo, Tei-Wei, Guan, Nan, Xue, Chun Jason
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 22.06.2025
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Neural image compression, necessary in various machine-to-machine communication scenarios, suffers from its heavy encode-decode structures and inflexibility in switching between different compression levels. Consequently, it raises significant challenges in applying the neural image compression to edge devices that are developed for powerful servers with high computational and storage capacities. We take a step to solve the challenges by proposing a new transformer-based edge-computefree image coding framework called Easz. Easz shifts the computational overhead to the server, and hence avoids the heavy encoding and model switching overhead on the edge. Easz utilizes a patch-erase algorithm to selectively remove image contents using a conditional uniform-based sampler. The erased pixels are reconstructed on the receiver side through a transformer-based framework. To further reduce the computational overhead on the receiver, we then introduce a lightweight transformer-based reconstruction structure to reduce the reconstruction load on the receiver side. Extensive evaluations conducted on a realworld testbed demonstrate multiple advantages of Easz over existing compression approaches, in terms of adaptability to different compression levels, computational efficiency, and image reconstruction quality.
AbstractList Neural image compression, necessary in various machine-to-machine communication scenarios, suffers from its heavy encode-decode structures and inflexibility in switching between different compression levels. Consequently, it raises significant challenges in applying the neural image compression to edge devices that are developed for powerful servers with high computational and storage capacities. We take a step to solve the challenges by proposing a new transformer-based edge-computefree image coding framework called Easz. Easz shifts the computational overhead to the server, and hence avoids the heavy encoding and model switching overhead on the edge. Easz utilizes a patch-erase algorithm to selectively remove image contents using a conditional uniform-based sampler. The erased pixels are reconstructed on the receiver side through a transformer-based framework. To further reduce the computational overhead on the receiver, we then introduce a lightweight transformer-based reconstruction structure to reduce the reconstruction load on the receiver side. Extensive evaluations conducted on a realworld testbed demonstrate multiple advantages of Easz over existing compression approaches, in terms of adaptability to different compression levels, computational efficiency, and image reconstruction quality.
Author Li, Jingzong
Xue, Chun Jason
Kuo, Tei-Wei
Xu, Hong
Wang, Jun
Mao, Yu
Guan, Nan
Author_xml – sequence: 1
  givenname: Yu
  surname: Mao
  fullname: Mao, Yu
  email: yu.mao@mbzuai.ac.ae
  organization: Mohamed bin Zayed University of Artificial Intelligence,UAE
– sequence: 2
  givenname: Jingzong
  surname: Li
  fullname: Li, Jingzong
  email: jingzongli@hsu.edu.hk
  organization: The Hang Seng University of Hong Kong,Hong Kong
– sequence: 3
  givenname: Jun
  surname: Wang
  fullname: Wang, Jun
  email: jwang699-c@my.cityu.edu.hk
  organization: City University of Hong Kong,Hong Kong
– sequence: 4
  givenname: Hong
  surname: Xu
  fullname: Xu, Hong
  email: hongxu@cuhk.edu.hk
  organization: The Chinese University of Hong Kong,Hong Kong
– sequence: 5
  givenname: Tei-Wei
  surname: Kuo
  fullname: Kuo, Tei-Wei
  email: ktw@csie.ntu.edu.tw
  organization: National Taiwan University,Taiwan
– sequence: 6
  givenname: Nan
  surname: Guan
  fullname: Guan, Nan
  email: nanguan@my.cityu.edu.hk
  organization: City University of Hong Kong,Hong Kong
– sequence: 7
  givenname: Chun Jason
  surname: Xue
  fullname: Xue, Chun Jason
  email: jason.xue@mbzuai.ac.ae
  organization: Mohamed bin Zayed University of Artificial Intelligence,UAE
BookMark eNo1j11LwzAYhSPohc79A5H8gc58NU28K3Wbg4Eg9cab8TZ9M4prMpKJ6K-3ol4dOJznwHNFzkMMSMgtZwvOmb17qBstjbILwUQ5VVwKrcozMreVNVLykkmmzCV5XUL-uqd1oPV-OCBtE4TsYxoxFR1k7OlmhD3SJo7HhDkPMdBVghE_Ynqj05A-Y47vyWHhYsinBEP4gWKbr8mFh0PG-V_OyMtq2TaPxfZpvWnqbQG8sqdCghBKgXRCoOIWJPfAOuUqb5nqe8c7Zj2C4h0apTVoqFRl_KTlwYADOSM3v78DIu6OaRghfe7-leU35bFRUQ
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/DAC63849.2025.11132645
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://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331503048
EndPage 7
ExternalDocumentID 11132645
Genre orig-research
GroupedDBID 6IE
6IH
CBEJK
RIE
RIO
ID FETCH-LOGICAL-a179t-3a2244a3c22e419a31fa0b4c7f904ddc1b09fea41be8466a6a7478f025fa8aca3
IEDL.DBID RIE
IngestDate Wed Oct 01 07:05:15 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a179t-3a2244a3c22e419a31fa0b4c7f904ddc1b09fea41be8466a6a7478f025fa8aca3
PageCount 7
ParticipantIDs ieee_primary_11132645
PublicationCentury 2000
PublicationDate 2025-June-22
PublicationDateYYYYMMDD 2025-06-22
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-June-22
  day: 22
PublicationDecade 2020
PublicationTitle 2025 62nd ACM/IEEE Design Automation Conference (DAC)
PublicationTitleAbbrev DAC
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
Score 2.2950559
Snippet Neural image compression, necessary in various machine-to-machine communication scenarios, suffers from its heavy encode-decode structures and inflexibility in...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Computational efficiency
Erase-and-Squeeze
Image coding
Image Compression
Image edge detection
Image reconstruction
Machine-to-machine communications
Performance evaluation
Receivers
Servers
Switches
Transformer-based Auto-Encoder
Transformers
Title Easz: An Agile Transformer-based Image Compression Framework for Resource-constrained IoTs
URI https://ieeexplore.ieee.org/document/11132645
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELVoxcAEiCK-5YHVbT6cuGarSiuQUNWhoIqlOjtnxECK0paBX4_PaUAMDGyR5cjSxZd3cd67x9i18t8AziYonEIjfP1vBGSZFc5jqQT0kBQ8lp4e1GTSn8_1dCtWD1oYRAzkM-zSZfiXXyztho7KesEWPZdZi7WUymux1lb1G0e6dzsY-t0kSX6SZN1m8i_blIAa4_1_rnfAOj_6Oz79RpZDtoPlEXsewerzhg9KPnjxqcxnTcmJlSAsKvj9m385cMrwmtxa8nFDveJ-Im-O6oWlopC8Ieim5WzVYY_j0Wx4J7bOCAJ8Aq1FCh55JaQ2SVDGGtLYQWSkVU5HsihsbCLtEGRs0NcXOeRAbfKdD4uDPlhIj1m7XJZ4wriKQGn0We6o9ZvumxQBlKG-YcRMVaesQ4FZvNfNLxZNTM7-GD9nexR-YlMlyQVrr6sNXrJd-7F-XVVX4ZF9AYBXmSQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELWgIMEEiCK-8cDqNh9OXbNVpVUrStUhoIqlOjtn1IEU9YOBX48vbUAMDGxR5MjSOed3cd67x9it8t8AzkYonEIjfP1vBCSJFc5jqQT0kFR4LD0P1HDYHI_1aCNWL7QwiFiQz7BGl8W__GxmV3RUVi9s0Rsy2WY7iZRRsJZrbXS_YaDr9622f58kCVCipFYO_2WcUuBG9-CfMx6y6o8Cj4--seWIbWF-zF46sPi8462ct159MvO0LDpxLgiNMt5_89sDpxxf01tz3i3JV9wP5OVhvbBUFpI7BD00SxdV9tTtpO2e2HgjCPAptBQxeOyVENsoQhlqiEMHgZFWOR3ILLOhCbRDkKFBX2E0oAHUKN_5sDhogoX4hFXyWY6njKsAlEaf546av-mmiRFAGeocRtxUdcaqFJjJ-7r9xaSMyfkf92_YXi99HEwG_eHDBdunpSBuVRRdsspyvsIrtms_ltPF_LpYvi-m1Jxr
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=2025+62nd+ACM%2FIEEE+Design+Automation+Conference+%28DAC%29&rft.atitle=Easz%3A+An+Agile+Transformer-based+Image+Compression+Framework+for+Resource-constrained+IoTs&rft.au=Mao%2C+Yu&rft.au=Li%2C+Jingzong&rft.au=Wang%2C+Jun&rft.au=Xu%2C+Hong&rft.date=2025-06-22&rft.pub=IEEE&rft.spage=1&rft.epage=7&rft_id=info:doi/10.1109%2FDAC63849.2025.11132645&rft.externalDocID=11132645