• Home
  • Search
  • Boosting Generalization of Semantic Segmentation With Unseen Style Seeking-Based Meta-Learning.
  • Cite Icon1
  • https://doi.org/10.1109/tnnls.2025.3560263Copy DOI Icon

Boosting Generalization of Semantic Segmentation With Unseen Style Seeking-Based Meta-Learning.

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

This article considers a worst and most challenging scene in domain generalization (DG), where a model aims to generalize well on unseen domains while only one single domain is available for training. Existing randomization-based methods achieve this goal by enriching the style of the training data. However, they fail to guarantee the diversity of newly generated data required for generalization and thus lead to insufficient expansion of the training distribution. Thus, we propose a novel single DG (SDG) framework, unseen style seeking-based meta-learning (USSML). In USSML, multiple plausible domains with various styles are first constructed from a single source domain and the combination is performed across generated domains to emulate unseen images, extending the distribution boundaries of the source domain. The domain combination is performed at two levels, i.e., global and instance, to meet the generalization challenge in semantic segmentation. Then, the generated diverse domains are further exploited to force the model to optimize in an unbiased manner across all domains by relearning regions lacking domain-invariant representation capability, driving the model toward domain invariance. A point worth mentioning is that the proposed method is easily integrated into existing segmentation methods with little computational cost to improve their generalization. Extensive experiments are conducted on five popular segmentation datasets and the results have verified the effectiveness of USSML in improving the model's generalization and the superiority of USSML over existing works.

Similar Papers
  • Conference Article
  • Citations1

ProMEA: Prompt-driven Expansion and Alignment for Single Domain Generalization

  • Aug 01, 2024
  • Yunyun Wang +3
  • Research Article
  • Citations547

Generalizing Deep Learning for Medical Image Segmentation to Unseen Domains via Deep Stacked Transformation.

  • Feb 12, 2020
  • IEEE transactions on medical imaging
  • Ling Zhang +10
  • Research Article
  • Citations11

Soft labeling constraint for generalizing from sentiments in single domain

  • Feb 24, 2022
  • Knowledge-Based Systems
  • Abhinaba Roy +1
  • Research Article
  • Citations1

Single-Domain Generalization via Path Flatness-Aware Optimization of Loss Landscapes.

  • Mar 01, 2026
  • IEEE transactions on neural networks and learning systems
  • Zizhou Wang +7
  • Research Article

Frequency-aware domain randomization for single-source domain generalization in medical image segmentation.

  • Nov 29, 2025
  • Medical physics
  • Jiayi Wu +6
  • Research Article

Toward Enhanced Representation Learning for Single-Source Domain Generalization in LiDAR Semantic Segmentation.

  • Jun 01, 2026
  • IEEE transactions on pattern analysis and machine intelligence
  • Hyeonseong Kim +3
  • Research Article
  • Citations4

Phrase Grounding-Based Style Transfer for Single-Domain Generalized Object Detection

  • Jan 01, 2026
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Hao Li +8
  • Research Article
  • Citations20

Single Domain Generalization Method for Remote Sensing Image Segmentation via Category Consistency on Domain Randomization

  • Jan 01, 2024
  • IEEE Transactions on Geoscience and Remote Sensing
  • Chenbin Liang +3
  • Research Article
  • Citations12

When Neural Networks Fail to Generalize? A Model Sensitivity Perspective

  • Jun 26, 2023
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Jiajin Zhang +6
  • Research Article
  • Citations7

Adaptive Domain Generalization Via Online Disagreement Minimization.

  • Jan 01, 2023
  • IEEE Transactions on Image Processing
  • Xin Zhang +1
  • Research Article

Projection Reconstruction Based Domain-Adaptive Dictionary Pair Learning Method

  • Jul 01, 2025
  • Journal of Computer-Aided Design & Computer Graphics
  • Guohua Zhou +5
  • Conference Article
  • Citations65

StandardGAN: Multi-source Domain Adaptation for Semantic Segmentation of Very High Resolution Satellite Images by Data Standardization

  • Jun 01, 2020
  • Onur Tasar +4
  • Research Article
  • Citations41

Dynamic Classifier Alignment for Unsupervised Multi-Source Domain Adaptation

  • Jan 01, 2022
  • IEEE Transactions on Knowledge and Data Engineering
  • Keqiuyin Li +3
  • Research Article
  • Citations31

Learning Across Tasks for Zero-Shot Domain Adaptation From a Single Source Domain.

  • Oct 01, 2022
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Jinghua Wang +1
  • Research Article

Enhancing Deforestation Detection Through Multi-Domain Adaptation with Uncertainty Estimation

  • Apr 26, 2025
  • Forests
  • Luiz Fernando De Moura +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.