Implementation and Analysis on Backpropagating Refinement Scheme for Interactive Image Segmentation

Chaewon Lee, Won Dong Jang, Chang Su Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

BRS is the first CNN-based interactive image segmentation algorithm to refine segmentation results based on a backpropagation scheme. In this paper, we give a detailed description of how BRS operates and demonstrate how to implement the algorithm. In BRS, user-provided clicks are first converted into interaction maps, which are then concatenated with the RGB image and provided as input to a segmentation network. In the test phase, performing the forward pass in the network generates an initial segmentation map. However, the user-annotated pixels may be mislabeled in the initial result. BRS refines this result by correcting the mislabeled pixels. We implement this BRS algorithm in PyTorch and publish the source codes. Moreover, we first show that BRS can reach the perfect IoU ratio of 1.0 in most cases and delineate objects more accurately than a variant of BRS, called f-BRS.

Original languageEnglish
Title of host publication2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages696-702
Number of pages7
ISBN (Electronic)9798350300673
DOIs
Publication statusPublished - 2023
Event2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023 - Taipei, Taiwan, Province of China
Duration: 2023 Oct 312023 Nov 3

Publication series

Name2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023

Conference

Conference2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023
Country/TerritoryTaiwan, Province of China
CityTaipei
Period23/10/3123/11/3

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

ASJC Scopus subject areas

  • Hardware and Architecture
  • Signal Processing
  • Artificial Intelligence
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Implementation and Analysis on Backpropagating Refinement Scheme for Interactive Image Segmentation'. Together they form a unique fingerprint.

Cite this