Data augmentation (DA) is indispensable in modern machine learning and deep neural
networks. The basic idea of DA is to construct new training data to improve the model's …

The challenge of semantic segmentation in Unsupervised Domain Adaptation (UDA)
emerges not only from domain shifts between source and target images but also from …

Semi-supervised cross-domain segmentation, also referred to as Semi-supervised domain
adaptation (SSDA), aims to bridge the domain gap and enhance model performance on the …

Existing domain generalization semantic segmentation (DGSS) methods have achieved
remarkable performance on unseen domains by generating stylized images to increase the …

Recently, domain adaptation (DA) methods based on contrastive learning are widely used to
solve the cross-scene classification problem. However, existing contrastive learning …

Current state-of-the-art dialogue systems heavily rely on extensive training datasets.
However, challenges arise in domains where domain-specific training datasets are …

Unsupervised Domain Adaptation (UDA) aims to transfer knowledge learned from a labeled
source domain to an unlabeled target domain. While UDA methods for synthetic to real …

Multi-target domain adaptation (MTDA) for semantic segmentation poses a significant
challenge, as it involves multiple target domains with varying distributions. The goal of …

Pixel-level manual annotations are expensive and time-consuming to obtain for semantic
segmentation tasks. Unsupervised domain adaptation (UDA), which outperforms direct zero …

현실에서 획득한 이미지에 대해 시멘틱 세그멘테이션 라벨을 만드는 것은 매우 비용이
많이든다. 비지도 도메인 적응에서는 이러한 문제를 해결하기 위해 라벨을 쉽게 수집할 수 있는 …