Related papers: Dual Moving Average Pseudo-Labeling for Source-Fre…

Unsupervised domain adaptation tackles the problem that domain shifts between training and test data impair the performance of neural networks in many real-world applications. Thereby, in realistic scenarios, the source data may no longer…

Self-supervised learning of speech representations has been a very active research area but most work is focused on a single domain such as read audio books for which there exist large quantities of labeled and unlabeled data. In this…

Domain adaptation is a critical task in machine learning that aims to improve model performance on a target domain by leveraging knowledge from a related source domain. In this work, we introduce Universal Semi-Supervised Domain Adaptation…

The success of deep learning in computer vision is mainly attributed to an abundance of data. However, collecting large-scale data is not always possible, especially for the supervised labels. Unsupervised domain adaptation (UDA) aims to…

Unsupervised domain adaption (UDA) aims to adapt models learned from a well-annotated source domain to a target domain, where only unlabeled samples are given. Current UDA approaches learn domain-invariant features by aligning source and…

It is desirable to transfer the knowledge stored in a well-trained source model onto non-annotated target domain in the absence of source data. However, state-of-the-art methods for source free domain adaptation (SFDA) are subject to strict…

Pseudo-labels are confident predictions made on unlabeled target data by a classifier trained on labeled source data. They are widely used for adapting a model to unlabeled data, e.g., in a semi-supervised learning setting. Our key insight…

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Owing to privacy concerns and heavy data transmission, source-free UDA, exploiting the pre-trained source models…

Domain adaptation (DA) addresses the real-world image classification problem of discrepancy between training (source) and testing (target) data distributions. We propose an unsupervised DA method that considers the presence of only…

Source-Free Domain Adaptation (SFDA) enables domain adaptation for semantic segmentation of Remote Sensing Images (RSIs) using only a well-trained source model and unlabeled target domain data. However, the lack of ground-truth labels in…

Adapting a medical image segmentation model to a new domain is important for improving its cross-domain transferability, and due to the expensive annotation process, Unsupervised Domain Adaptation (UDA) is appealing where only unlabeled…

Source-free domain adaptation aims to adapt deep neural networks using only pre-trained source models and target data. However, accessing the source model still has a potential concern about leaking the source data, which reveals the…

3D object detection networks tend to be biased towards the data they are trained on. Evaluation on datasets captured in different locations, conditions or sensors than that of the training (source) data results in a drop in model…

Unsupervised domain adaptation techniques have been successful for a wide range of problems where supervised labels are limited. The task is to classify an unlabeled `target' dataset by leveraging a labeled `source' dataset that comes from…

Domain Generalization (DG) aims to generalize a model trained on multiple source domains to an unseen target domain. The source domains always require precise annotations, which can be cumbersome or even infeasible to obtain in practice due…

Deep Neural Networks have significantly impacted many computer vision tasks. However, their effectiveness diminishes when test data distribution (target domain) deviates from the one of training data (source domain). In situations where…

Although deep neural networks have achieved remarkable results for the task of semantic segmentation, they usually fail to generalize towards new domains, especially when performing synthetic-to-real adaptation. Such domain shift is…

Domain adaptation has shown appealing performance by leveraging knowledge from a source domain with rich annotations. However, for a specific target task, it is cumbersome to collect related and high-quality source domains. In real-world…

Unsupervised domain adaptation targets to transfer task-related knowledge from labeled source domain to unlabeled target domain. Although tremendous efforts have been made to minimize domain divergence, most existing methods only partially…

Current unsupervised domain adaptation methods can address many types of distribution shift, but they assume data from the source domain is freely available. As the use of pre-trained models becomes more prevalent, it is reasonable to…