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 …
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
Existing domain generalization semantic segmentation (DGSS) methods aim to learn
domain-invariant representation from single or multiple domains by using the consistency …
domain-invariant representation from single or multiple domains by using the consistency …
Class-Balanced Sampling and Discriminative Stylization for Domain Generalization Semantic Segmentation
Existing domain generalization semantic segmentation (DGSS) methods have achieved
remarkable performance on unseen domains by generating stylized images to increase the …
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
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 …
between synthesized training samples and the real test images leads to significant …
Increase the sensitivity of moderate examples for semantic image segmentation
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 …
classification and do supervised training with the standard cross-entropy loss (CE). Although …
Joint Style and Layout Synthesizing: Toward Generalizable Remote Sensing Semantic Segmentation
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 …
aiming to generalize a model trained only on the source domain to unseen domains …
Local and Global Structure-Aware Contrastive Framework for Entity alignment
Entity alignment (EA) seeks to identify equivalent real-world entities across different
knowledge graphs. Recently, integrating graph neural networks (GNNs) with graph …
knowledge graphs. Recently, integrating graph neural networks (GNNs) with graph …
Layout Relationship Decoupling Framework for Multi-target Domain Adaptative Semantic Segmentation
Single-Target Unsupervised Domain Adaptative (ST-UDA) semantic segmentation has
achieved enlightening performance, while it suffers from performance degradation in multi …
achieved enlightening performance, while it suffers from performance degradation in multi …