• Home
  • Search
  • Cell Segmentation Without Annotation by Unsupervised Domain Adaptation Based on Cooperative Self-Learning
  • https://doi.org/10.1109/access.2026.3657610Copy DOI Icon

Cell Segmentation Without Annotation by Unsupervised Domain Adaptation Based on Cooperative Self-Learning

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Semantic cell segmentation from microscopic images is essential for the quantitative evaluation of cell morphology. Although supervised deep-learning-based models offer accurate segmentation, their performance degrades for unknown cell types. To address this problem, unsupervised domain adaptation methods based on adversarial training, self-training, or a combination of these approaches have been developed in recent years. These methods train the model using inference labels from the unknown domain as pseudo labels with reliability to resolve the discrepancy between the features of the unknown and known domains. However, conventional methods require a predefined threshold to calculate pseudo-label reliability, leading to costly hyperparameter tuning. Here, we developed an unsupervised domain adaptation for semantic cell segmentation with cooperative self-learning (CULPICO: Cooperative Unsupervised Learning for PIxel-wise COloring) that does not require a predefined threshold of pseudo-label reliability. The proposed method consists of two independent segmentation models and a mutual exchange mechanism of inference data. The models infer a label probability at each pixel and generate a pseudo-label as unsupervised learning. The pseudo-labels created by each model are mutually used as ground truth in the other model. Loss function is corrected by considering pixel-level discrepancies between the label probabilities inferred by the two models. The proposed method, despite being an unsupervised learning method, can efficiently segment unknown cell types without labels with an accuracy comparable to that of supervised learning models: Our model increased the intersection-over-union (IoU) metric by up to 0.652 (from 0.156 to 0.808). Performance efficiency with respect to the number of model parameters was higher in our model than in existing unsupervised domain adaptation methods. We expect our method, which could solve the performance degradation problem without constructing new datasets, to accelerate life science by reducing the cost of extracting quantitative biological knowledge.

Similar Papers
  • PDF
  • Research Article
  • Citations55

The Eyes of the Gods: A Survey of Unsupervised Domain Adaptation Methods Based on Remote Sensing Data

  • Sep 03, 2022
  • Remote Sensing
  • Mengqiu Xu +4
  • Research Article
  • Citations4

Deep Learning-based Unsupervised Domain Adaptation via a Unified Model for Prostate Lesion Detection Using Multisite Biparametric MRI Datasets.

  • Sep 01, 2024
  • Radiology. Artificial intelligence
  • Hao Li +18
  • Research Article
  • Citations2

Orchard Areas Segmentation in Remote Sensing Images via Class Feature Aggregate Discriminator

  • Jan 01, 2022
  • IEEE Geoscience and Remote Sensing Letters
  • Ming Liu +4
  • Research Article
  • Citations2

Rethinking unsupervised domain adaptation for semantic segmentation

  • Oct 01, 2024
  • Pattern Recognition Letters
  • Zhijie Wang +2
  • Conference Article
  • Citations78

Collaborative Optimization and Aggregation for Decentralized Domain Generalization and Adaptation

  • Oct 01, 2021
  • Guile Wu +1
  • Research Article
  • Citations75

Multisource domain factorization network for cross-domain fault diagnosis of rotating machinery: An unsupervised multisource domain adaptation method

  • Jul 24, 2021
  • Mechanical Systems and Signal Processing
  • Yaowei Shi +5
  • Research Article
  • Citations8

Unsupervised domain adaptation for the semantic segmentation of remote sensing images via a class-aware Fourier transform and a fine-grained discriminator

  • May 09, 2024
  • Digital Signal Processing
  • Sarmad F Ismael +2
  • Book Chapter
  • Citations3

Reliable Domain Adaptation with Classifiers Competition

  • Jan 01, 2019
  • Jingru Fu +1
  • Book Chapter
  • Citations3

Unsupervised Adaptation of Polyp Segmentation Models via Coarse-to-Fine Self-Supervision

  • Jan 01, 2023
  • Jiexiang Wang +1
  • Research Article
  • Citations3

Unsupervised deep consistency learning adaptation network for cardiac cross-modality structural segmentation.

  • Jul 14, 2023
  • Medical & biological engineering & computing
  • Dapeng Li +3
  • Book Chapter
  • Citations3

Self-supervision based Semantic Alignment for Unsupervised Domain Adaptation

  • Jan 01, 2022
  • Ronghang Zhu +1
  • Research Article
  • Citations10

Video domain adaptation for semantic segmentation using perceptual consistency matching

  • Jul 03, 2024
  • Neural Networks
  • Ihsan Ullah +6
  • Research Article
  • Citations15

A bidirectional multilayer contrastive adaptation network with anatomical structure preservation for unpaired cross-modality medical image segmentation

  • Aug 19, 2022
  • Computers in Biology and Medicine
  • Hong Liu +4
  • PDF
  • Research Article
  • Citations3

SFDA-CD: A Source-Free Unsupervised Domain Adaptation for VHR Image Change Detection

  • Apr 04, 2024
  • Remote Sensing
  • Jingxuan Wang +1
  • PDF
  • Supplementary Content
  • Citations67

Deep Unsupervised Domain Adaptation with Time Series Sensor Data: A Survey

  • Jul 23, 2022
  • Sensors (Basel, Switzerland)
  • Yongjie Shi +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.