Learning generalized visual relations for domain generalization semantic segmentation

Z Li, M Liao - Expert Systems with Applications, 2025 - Elsevier
Abstract Domain generalization semantic segmentation (DGSS) methods aim to generalize
well on out-of-distribution scenes, which is crucial for real-world applications. The key to …

Considering representation diversity and prediction consistency for domain generalization semantic segmentation

M Liao, S Tian, Y Zhang, G Hua, W Zou, X Li - Knowledge-Based Systems, 2024 - Elsevier
Existing domain generalization semantic segmentation (DGSS) methods aim to learn
domain-invariant representation from single or multiple domains by using the consistency …

Class-Balanced Sampling and Discriminative Stylization for Domain Generalization Semantic Segmentation

M Liao, S Tian, B Wei, Y Zhang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Existing domain generalization semantic segmentation (DGSS) methods have achieved
remarkable performance on unseen domains by generating stylized images to increase the …

A contrast-invariant feature extraction framework for single-domain generalization in infrared small target detection

W Chi, J Liu, X Lu, Y Ni, X Wang - Knowledge-Based Systems, 2025 - Elsevier
Infrared small target detection has important applications in many fields, but the domain gap
between synthesized training samples and the real test images leads to significant …

Increase the sensitivity of moderate examples for semantic image segmentation

Q Tang, F Liu, D Zhang, J Jiang, X Tang… - Image and Vision …, 2025 - Elsevier
Dominant paradigms in modern semantic segmentation resort to the scheme of pixel-wise
classification and do supervised training with the standard cross-entropy loss (CE). Although …

Joint Style and Layout Synthesizing: Toward Generalizable Remote Sensing Semantic Segmentation

Q Zang, S Wang, D Zhao, Z Zhong… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
This paper studies the domain generalized remote sensing semantic segmentation (RSSS),
aiming to generalize a model trained only on the source domain to unseen domains …

Local and Global Structure-Aware Contrastive Framework for Entity alignment

C Wang, W Wang, Q Liang, G Gao - Neurocomputing, 2025 - Elsevier
Entity alignment (EA) seeks to identify equivalent real-world entities across different
knowledge graphs. Recently, integrating graph neural networks (GNNs) with graph …

Layout Relationship Decoupling Framework for Multi-target Domain Adaptative Semantic Segmentation

Y Zhang, C Yang, M Liao, S Tian, W Zou… - Proceedings of the 6th …, 2024 - dl.acm.org
Single-Target Unsupervised Domain Adaptative (ST-UDA) semantic segmentation has
achieved enlightening performance, while it suffers from performance degradation in multi …