Related papers: IDPL: Intra-subdomain adaptation adversarial learn…

Semantic segmentation suffers from significant performance degradation when the trained network is applied to a different domain. To address this issue, unsupervised domain adaptation (UDA) has been extensively studied. Despite the…

Supervised deep learning requires massive labeled datasets, but obtaining annotations is not always easy or possible, especially for dense tasks like semantic segmentation. To overcome this issue, numerous works explore Unsupervised Domain…

Semantic image segmentation is a central and challenging task in autonomous driving, addressed by training deep models. Since this training draws to a curse of human-based image labeling, using synthetic images with automatically generated…

Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively generates pseudo labels on unlabeled target data and retrains the network. However, realistic segmentation datasets are highly imbalanced, pseudo…

Point cloud classification is a popular task in 3D vision. However, previous works, usually assume that point clouds at test time are obtained with the same procedure or sensor as those at training time. Unsupervised Domain Adaptation (UDA)…

To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation. However, the existence of false pseudo-labels, which may have a detrimental influence on learning…

The majority of existing Unsupervised Domain Adaptation (UDA) methods presumes source and target domain data to be simultaneously available during training. Such an assumption may not hold in practice, as source data is often inaccessible…

Methods for unsupervised domain adaptation (UDA) help to improve the performance of deep neural networks on unseen domains without any labeled data. Especially in medical disciplines such as histopathology, this is crucial since large…

Due to the few annotated labels of 3D point clouds, how to learn discriminative features of point clouds to segment object instances is a challenging problem. In this paper, we propose a simple yet effective 3D instance segmentation…

Recent advances in unsupervised domain adaptation have seen considerable progress in semantic segmentation. Existing methods either align different domains with adversarial training or involve the self-learning that utilizes pseudo labels…

This paper describes a method of domain adaptive training for semantic segmentation using multiple source datasets that are not necessarily relevant to the target dataset. We propose a soft pseudo-label generation method by integrating…

Although existing semantic segmentation approaches achieve impressive results, they still struggle to update their models incrementally as new categories are uncovered. Furthermore, pixel-by-pixel annotations are expensive and…

We introduce an unsupervised domain adaption (UDA) strategy that combines multiple image translations, ensemble learning and self-supervised learning in one coherent approach. We focus on one of the standard tasks of UDA in which a semantic…

Self-training is a competitive approach in domain adaptive segmentation, which trains the network with the pseudo labels on the target domain. However inevitably, the pseudo labels are noisy and the target features are dispersed due to the…

Semantic segmentation is one of the most fundamental problems in computer vision with significant impact on a wide variety of applications. Adversarial learning is shown to be an effective approach for improving semantic segmentation…

Unsupervised domain adaptation (UDA) for semantic segmentation addresses the cross-domain problem with fine source domain labels. However, the acquisition of semantic labels has always been a difficult step, many scenarios only have weak…

The cross-domain performance of automatic speech recognition (ASR) could be severely hampered due to the mismatch between training and testing distributions. Since the target domain usually lacks labeled data, and domain shifts exist at…

Unsupervised domain adaptation (UDA) typically carries out knowledge transfer from a label-rich source domain to an unlabeled target domain by adversarial learning. In principle, existing UDA approaches mainly focus on the global…

In semi-supervised domain adaptation (SSDA), a few labeled target samples of each class help the model to transfer knowledge representation from the fully labeled source domain to the target domain. Many existing methods ignore the benefits…

Recent advances in unsupervised domain adaptation (UDA) show that transferable prototypical learning presents a powerful means for class conditional alignment, which encourages the closeness of cross-domain class centroids. However, the…