Task Agnostic Cost Prediction Module for Semantic Labeling in Active Learning

Srikumar Sastry*, Nathan Jacobs, Mariana Belgiu, Raian Vargas Maretto

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

65 Downloads (Pure)

Abstract

We consider the problem of cost effective active learning for semantic segmentation, which aims at reducing the efforts of semantically annotating images. Current studies have ignored the inclusion of cost of labeling into their active learning frameworks. To this end, we first present a novel cost prediction module based on what we call the M-Net. M-Net combines the power of unsupervised W-Net and supervised U-Net to compute a refined segmentation map. The refined segmentation map is used to estimate the cost of annotations. The cost of annotation is estimated by the number of clicks required to annotate an image. To solve this task, we make use of the harris corner detector algorithm to estimate the location of the clicks required to annotate an image. Finally, we employ a multi armed bandit setting to minimize the cost of annotations while maximizing the performance of the semantic segmentation task. The M-Net outperforms fully supervised U-Net with +4.37 Acc and +3.75 mIoU. The proposed active learning framework also outperforms the existing baselines to prove the relevance of the approach in the current paradigm.

Original languageEnglish
Title of host publicationIGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
PublisherIEEE
Pages4990-4993
Number of pages4
ISBN (Electronic)9798350320107
DOIs
Publication statusPublished - 2023
Event43rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 - Pasadena Convention Center, Pasadena, United States
Duration: 16 Jul 202321 Jul 2023
Conference number: 43
https://2023.ieeeigarss.org/index.php

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
Volume2023-July

Conference

Conference43rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023
Abbreviated titleIGARSS 2023
Country/TerritoryUnited States
CityPasadena
Period16/07/2321/07/23
Internet address

Keywords

  • Active Learning
  • Semantic Segmentation
  • Uncertainty
  • 2024 OA procedure

Fingerprint

Dive into the research topics of 'Task Agnostic Cost Prediction Module for Semantic Labeling in Active Learning'. Together they form a unique fingerprint.

Cite this