相关论文: Source-free Domain Adaptation Requires Penalized D…

Domain adaptation (DA) aims to alleviate the domain shift between source domain and target domain. Most DA methods require access to the source data, but often that is not possible (e.g. due to data privacy or intellectual property). In…

Human Pose Estimation (HPE) is widely used in various fields, including motion analysis, healthcare, and virtual reality. However, the great expenses of labeled real-world datasets present a significant challenge for HPE. To overcome this,…

Source-free domain adaptation (SFDA) aims to adapt a model trained on labelled data in a source domain to unlabelled data in a target domain without access to the source-domain data during adaptation. Existing methods for SFDA leverage…

Deep neural networks suffer from performance decay when there is domain shift between the labeled source domain and unlabeled target domain, which motivates the research on domain adaptation (DA). Conventional DA methods usually assume that…

Most existing studies on unsupervised domain adaptation (UDA) assume that each domain's training samples come with domain labels (e.g., painting, photo). Samples from each domain are assumed to follow the same distribution and the domain…

Semi-supervised domain adaptation (SSDA) aims at training a high-performance model for a target domain using few labeled target data, many unlabeled target data, and plenty of auxiliary data from a source domain. Previous works in SSDA…

Source-free active domain adaptation (SFADA) addresses the challenge of adapting a pre-trained model to new domains without access to source data while minimizing the need for target domain annotations. This scenario is particularly…

A domain (distribution) shift between training and test data often hinders the real-world performance of deep neural networks, necessitating unsupervised domain adaptation (UDA) to bridge this gap. Online source-free UDA has emerged as a…

Source-free domain adaptation (SFDA) aims to address the challenge of adapting to a target domain without accessing the source domain directly. However, due to the inaccessibility of source domain data, deterministic invariable features…

We use information-theoretic tools to derive a novel analysis of Multi-source Domain Adaptation (MDA) from the representation learning perspective. Concretely, we study joint distribution alignment for supervised MDA with few target labels…

Domain Adaptation (DA) is important for deep learning-based medical image segmentation models to deal with testing images from a new target domain. As the source-domain data are usually unavailable when a trained model is deployed at a new…

Domain adaptation addresses the challenge of model performance degradation caused by domain gaps. In the typical setup for unsupervised domain adaptation, labeled data from a source domain and unlabeled data from a target domain are used to…

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…

Unsupervised domain adaptation (UDA) has increasingly gained interests for its capacity to transfer the knowledge learned from a labeled source domain to an unlabeled target domain. However, typical UDA methods require concurrent access to…

Semi-supervised domain adaptation (SSDA) adapts a learner to a new domain by effectively utilizing source domain data and a few labeled target samples. It is a practical yet under-investigated research topic. In this paper, we analyze the…

Domain generalization (DG) aims to generalize a model trained on multiple source (i.e., training) domains to a distributionally different target (i.e., test) domain. In contrast to the conventional DG that strictly requires the availability…

Heterogeneous domain adaptation (HDA) tackles the learning of cross-domain samples with both different probability distributions and feature representations. Most of the existing HDA studies focus on the single-source scenario. In reality,…

The generalization capability of unsupervised domain adaptation can mitigate the need for extensive pixel-level annotations to train semantic segmentation networks by training models on synthetic data as a source with computer-generated…

Given the emergence of deep learning, digital pathology has gained popularity for cancer diagnosis based on histology images. Deep weakly supervised object localization (WSOL) models can be trained to classify histology images according to…

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…