On-Device Unsupervised Image Segmentation

Along with the breakthrough of convolutional neural networks, in particular encoder-decoder and U-Net, learning-based segmentation has emerged in many research works. Most of them are based on supervised learning, requiring plenty of annotated data; however, to support segmentation, a label for each...

Full description

Saved in:
Bibliographic Details
Published in:2023 60th ACM/IEEE Design Automation Conference (DAC) pp. 1 - 6
Main Authors: Yang, Junhuan, Sheng, Yi, Zhang, Yuzhou, Jiang, Weiwen, Yang, Lei
Format: Conference Proceeding
Language:English
Published: IEEE 09.07.2023
Subjects:
Data privacy
Design automation
Encoding
Hyperdimensional Computing
Image color analysis
Image segmentation
On-device Learning
Performance evaluation
Supervised learning
Unsupervised Segmentation
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Along with the breakthrough of convolutional neural networks, in particular encoder-decoder and U-Net, learning-based segmentation has emerged in many research works. Most of them are based on supervised learning, requiring plenty of annotated data; however, to support segmentation, a label for each pixel is required, which is obviously expensive. As a result, the issue of lacking annotated segmentation data commonly exists. Continuous learning is a promising way to deal with this issue; however, it still has high demands on human labor for annotation. What's more, privacy is highly required in segmentation data for real-world applications, which further calls for on-device learning. In this paper, we aim to resolve the above issue in an alternative way: Instead of supervised segmentation, we propose to develop efficient unsupervised segmentation which can be executed on edge devices without annotated data. Based on our observation that segmentation can obtain high performance when pixels are mapped to a high-dimension space using their position and color information, we for the first time bring brain-inspired hyperdimensional computing (HDC) to the segmentation task. We build the HDC-based unsupervised segmentation framework, namely "SegHDC". In SegHDC, we devise a novel encoding approach, which follows the Manhattan distance. A clustering algorithm is further developed on top of the encoded high-dimension vectors to obtain segmentation results. Experimental results show that SegHDC can significantly surpass neural network-based unsupervised segmentation. On a standard segmentation dataset, DSB2018, SegHDC can achieve a 28.0% improvement in Intersection over Union (IoU) score; meanwhile, it achieves over 300× speedup on Raspberry PI. What's more, for a larger size image in the BBBC005 dataset, the existing approach cannot be accommodated to Raspberry PI due to out of memory; on the other hand, SegHDC can obtain segmentation results within 3 minutes while achieving a 0.9587 IoU score.
AbstractList Along with the breakthrough of convolutional neural networks, in particular encoder-decoder and U-Net, learning-based segmentation has emerged in many research works. Most of them are based on supervised learning, requiring plenty of annotated data; however, to support segmentation, a label for each pixel is required, which is obviously expensive. As a result, the issue of lacking annotated segmentation data commonly exists. Continuous learning is a promising way to deal with this issue; however, it still has high demands on human labor for annotation. What's more, privacy is highly required in segmentation data for real-world applications, which further calls for on-device learning. In this paper, we aim to resolve the above issue in an alternative way: Instead of supervised segmentation, we propose to develop efficient unsupervised segmentation which can be executed on edge devices without annotated data. Based on our observation that segmentation can obtain high performance when pixels are mapped to a high-dimension space using their position and color information, we for the first time bring brain-inspired hyperdimensional computing (HDC) to the segmentation task. We build the HDC-based unsupervised segmentation framework, namely "SegHDC". In SegHDC, we devise a novel encoding approach, which follows the Manhattan distance. A clustering algorithm is further developed on top of the encoded high-dimension vectors to obtain segmentation results. Experimental results show that SegHDC can significantly surpass neural network-based unsupervised segmentation. On a standard segmentation dataset, DSB2018, SegHDC can achieve a 28.0% improvement in Intersection over Union (IoU) score; meanwhile, it achieves over 300× speedup on Raspberry PI. What's more, for a larger size image in the BBBC005 dataset, the existing approach cannot be accommodated to Raspberry PI due to out of memory; on the other hand, SegHDC can obtain segmentation results within 3 minutes while achieving a 0.9587 IoU score.
Author Sheng, Yi
Jiang, Weiwen
Yang, Junhuan
Yang, Lei
Zhang, Yuzhou
Author_xml – sequence: 1
  givenname: Junhuan
  surname: Yang
  fullname: Yang, Junhuan
  email: jyang71@gmu.edu
  organization: George Mason University
– sequence: 2
  givenname: Yi
  surname: Sheng
  fullname: Sheng, Yi
  organization: George Mason University
– sequence: 3
  givenname: Yuzhou
  surname: Zhang
  fullname: Zhang, Yuzhou
  organization: Northeastern University
– sequence: 4
  givenname: Weiwen
  surname: Jiang
  fullname: Jiang, Weiwen
  organization: George Mason University
– sequence: 5
  givenname: Lei
  surname: Yang
  fullname: Yang, Lei
  email: lyang29@gmu.edu
  organization: George Mason University
BookMark eNo1j8tKw0AUQEdQUNv8gUi2LhIndx6Zuyyp1UKhC9t1mcedMmCmJYkF_15BXZ2zOnDu2XU-ZWLsseF103B8Xi46pRGwBg6ibjjIFhVesQJbNEJxAUKa5pYV45gc11wZybW8Y0_bXC3pkjyV-zx-nmm4pJFCue7tkcp3OvaUJzulU56zm2g_Rir-OGP71cuue6s229d1t9hUFpBPlfdgUcaoXEvaSYGuDQSAYFAYKwlUUCpY6YSPWpNHGchrxylK8-NazNjDbzcR0eE8pN4OX4f_I_ENQFlDfQ
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/DAC56929.2023.10247959
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Xplore Digital Library (LUT)
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 9798350323481
EndPage 6
ExternalDocumentID 10247959
Genre orig-research
GrantInformation_xml – fundername: National Institutes of Health
  funderid: 10.13039/100000002
GroupedDBID 6IE
6IH
ACM
ALMA_UNASSIGNED_HOLDINGS
CBEJK
RIE
RIO
ID FETCH-LOGICAL-a290t-cc2a94ff5b7e6b439b7de22928938a4e25d55da4b3cf66ec94dec6b0ef4894d63
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001073487300266&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:47:47 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a290t-cc2a94ff5b7e6b439b7de22928938a4e25d55da4b3cf66ec94dec6b0ef4894d63
PageCount 6
ParticipantIDs ieee_primary_10247959
PublicationCentury 2000
PublicationDate 2023-July-9
PublicationDateYYYYMMDD 2023-07-09
PublicationDate_xml – month: 07
  year: 2023
  text: 2023-July-9
  day: 09
PublicationDecade 2020
PublicationTitle 2023 60th ACM/IEEE Design Automation Conference (DAC)
PublicationTitleAbbrev DAC
PublicationYear 2023
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssib060584064
Score 2.2725222
Snippet Along with the breakthrough of convolutional neural networks, in particular encoder-decoder and U-Net, learning-based segmentation has emerged in many research...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Data privacy
Design automation
Encoding
Hyperdimensional Computing
Image color analysis
Image segmentation
On-device Learning
Performance evaluation
Supervised learning
Unsupervised Segmentation
Title On-Device Unsupervised Image Segmentation
URI https://ieeexplore.ieee.org/document/10247959
WOSCitedRecordID wos001073487300266&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/eLvHCXMwlV07T8MwED7RioEJEEFAAWVgYUhIHMeOR9RSgYRKJajUrfLjghiaVk3C78d2UxADA9vJkt_-fLbP3x3ADc9SJRSSCA2aiKbKQgqZBR5TMrEt18L4mX7mk0kxn4tpR1b3XBhE9J_PMHait-WblW7dU5lFOKEuNnYPepzzLVlrt3icec8qJ9qxgNNE3I3uhzmz6j92IcLjXeZfYVS8Fhkf_rP-Iwh--Hjh9FvTHMMeVidw-1JFI3RAD2dV3a4d6Gs04dPSbhHhK74vO1pRFcBs_PA2fIy6wAeRJCJpIq2JFLQsc8WRKXtkUNwgIcJejrJCUiS5yXMjqcp0yRhqQQ1qphIsaWFllp1Cv1pVeAah8-VCZGKUcfY1SQqWlIymxhaVE5TFOQSun4v11rfFYtfFiz_SB3DgRtN_WBWX0G82LV7Bvv5sPurNtZ-RLygAjFQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEJ4omuhJjRjf7sGLh8XdbtvdHg1IICKSCAk30ses4cBCYPH325ZF48GDt6ZJm07brzPtzNcBuE-TWAmFJESDJqSxspBCboHHlYzsyLUwfqV7ab-fjcdiUJHVPRcGEX3wGTZc0fvyzVyv3VOZRTihLjf2LuwxSkm8oWttt49z8Fn1RCsecByJx9ZTk3FrADRckvDGtvmvRCpej7SP_jmCY6j_MPKCwbeuOYEdLE7h4a0IW-igHoyK1XrhYL9CE3Rn9pAI3vFjVhGLijqM2s_DZiesUh-EkoioDLUmUtA8ZypFrqzRoFKDhAh7PUoySZEww5iRVCU65xy1oAY1VxHmNLNlnpxBrZgXeA6B-82FyMgo4zxskmQ8yjmNje2KEZTZBdSdnJPF5neLyVbEyz_q7-CgM3ztTXrd_ssVHLqZ9eGr4hpq5XKNN7CvP8vpannrV-cLqiOPmw
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=2023+60th+ACM%2FIEEE+Design+Automation+Conference+%28DAC%29&rft.atitle=On-Device+Unsupervised+Image+Segmentation&rft.au=Yang%2C+Junhuan&rft.au=Sheng%2C+Yi&rft.au=Zhang%2C+Yuzhou&rft.au=Jiang%2C+Weiwen&rft.date=2023-07-09&rft.pub=IEEE&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FDAC56929.2023.10247959&rft.externalDocID=10247959