• Home
  • Search
  • Reducing Annotation Effort by Identifying and Labeling Contextually Diverse Classes for Semantic Segmentation Under Domain Shift
  • Open Access IconOpen Access
  • Cite Icon3
  • https://doi.org/10.1109/wacv56688.2023.00585Copy DOI Icon

Reducing Annotation Effort by Identifying and Labeling Contextually Diverse Classes for Semantic Segmentation Under Domain Shift

  • Jan 1, 2023
  • Sharat Agarwal +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In Active Domain Adaptation (ADA), one uses Active Learning (AL) to select a subset of images from the target domain, which are then annotated and used for supervised domain adaptation (DA). Given the large performance gap between supervised and unsupervised DA techniques, ADA allows for an excellent trade-off between annotation cost and performance. Prior art makes use of measures of uncertainty or disagreement of models to identify ‘regions' to be annotated by the human oracle. However, these regions frequently comprise of pixels at object boundaries which are hard and tedious to annotate. Hence, even if the fraction of image pixels annotated reduces, the overall annotation time and the resulting cost still remain high. In this work, we propose an ADA strategy, which given a frame, identifies a set of classes that are hardest for the model to predict accurately, thereby recommending semantically meaningful regions to be annotated in a selected frame. We show that these set of ‘hard' classes are context-dependent and typically vary across frames, and when annotated help the model generalize better. We propose two ADA techniques: the Anchor-based and Augmentation-based approaches to select complementary and diverse regions in the context of the current training set. Our approach achieves 66.6 mIoU on GTA5 →Cityscapes dataset with an annotation budget of 4.7% in comparison to 64.9 mIoU by MADA [22] using 5% of annotations. Our technique can also be used as a decorator for any existing frame-based AL technique, e.g., we report 1.5% performance improvement for CDAL [1] on Cityscapes using our approach.

Similar Papers
  • Research Article
  • Citations37

Unsupervised Adversarial Domain Adaptation Network for Semantic Segmentation

  • Dec 26, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Wei Liu +1
  • Book Chapter
  • Citations3

Harmonised Segmentation of Neonatal Brain MRI: A Domain Adaptation Approach

  • Jan 01, 2020
  • Irina Grigorescu +6
  • Research Article
  • Citations3

Unsupervised global-local domain adaptation with self-training for remote sensing image semantic segmentation

  • Jan 20, 2025
  • International Journal of Remote Sensing
  • Junbo Zhang +3
  • Research Article
  • Citations4

Distributionally robust unsupervised domain adaptation

  • Jun 07, 2023
  • Journal of Computational and Applied Mathematics
  • Yibin Wang +1
  • PDF
  • Research Article
  • Citations33

Domain Adversarial Neural Networks for Large-Scale Land Cover Classification

  • May 14, 2019
  • Remote Sensing
  • Mesay Belete Bejiga +2
  • Research Article

PANDA: A Polarized Attention Network for Enhanced Unsupervised Domain Adaptation in Semantic Segmentation

  • Oct 31, 2024
  • Electronics
  • Chiao-Wen Kao +3
  • Book Chapter
  • Citations9

A New Bidirectional Unsupervised Domain Adaptation Segmentation Framework

  • Jan 01, 2021
  • Munan Ning +8
  • PDF
  • Research Article
  • Citations9

Unsupervised Domain Adaptation for Mitigating Sensor Variability and Interspecies Heterogeneity in Animal Activity Recognition

  • Oct 20, 2023
  • Animals : an Open Access Journal from MDPI
  • Seong-Ho Ahn +2
  • Preprint Article

Segmentation Cycle-GAN Loss for Structure-Preserving Domain Adaptation of Medical Images

  • Sep 06, 2024
  • Paolo Iacono
  • Preprint Article

Segmentation Cycle-GAN Loss for Structure-Preserving Domain Adaptation of Medical Images

  • Sep 06, 2024
  • Paolo Iacono
  • Research Article

Bi3D++: Hybrid Bi-Domain Active Learning for Cross-Domain 3D Object Detection.

  • Sep 01, 2026
  • IEEE transactions on pattern analysis and machine intelligence
  • Jiakang Yuan +6
  • Research Article
  • Citations81

LE-UDA: Label-efficient unsupervised domain adaptation for medical image segmentation.

  • Mar 01, 2023
  • IEEE Transactions on Medical Imaging
  • Ziyuan Zhao +5
  • PDF
  • Research Article
  • Citations4

Class-wise histogram matching-based domain adaptation in deep learning-based bridge element segmentation

  • May 03, 2025
  • Journal of Civil Structural Health Monitoring
  • Tarutal Ghosh Mondal +3
  • Abstract

Unsupervised Domain Adaptation of Auto-Segmentation on Multi-Source MRIs

  • Sep 29, 2023
  • International Journal of Radiation Oncology*Biology*Physics
  • W Zhang +4
  • Research Article

SPD-DANN: An SPD manifold unsupervised domain adaptation method for cross subject motor imagery EEG decoding.

  • Oct 01, 2026
  • Neural networks : the official journal of the International Neural Network Society
  • Junshi Cheng +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.