Related papers: Proxy Denoising for Source-Free Domain Adaptation

Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain by reducing the cross-domain distribution discrepancy. Most prior DA approaches leverage complicated and powerful deep neural…

Unsupervised domain adaptation aims to transfer knowledge from a source domain to a target domain so that the target domain data can be recognized without any explicit labelling information for this domain. One limitation of the problem…

While huge volumes of unlabeled data are generated and made available in many domains, the demand for automated understanding of visual data is higher than ever before. Most existing machine learning models typically rely on massive amounts…

In theory, the success of unsupervised domain adaptation (UDA) largely relies on domain gap estimation. However, for source free UDA, the source domain data can not be accessed during adaptation, which poses great challenge of measuring the…

Unsupervised domain adaptation (DA) has gained substantial interest in semantic segmentation. However, almost all prior arts assume concurrent access to both labeled source and unlabeled target, making them unsuitable for scenarios…

Conventional Domain Adaptation (DA) methods aim to learn domain-invariant feature representations to improve the target adaptation performance. However, we motivate that domain-specificity is equally important since in-domain trained models…

Open Set Domain Adaptation (OSDA) aims to adapt a model trained on a source domain to a target domain that undergoes distribution shift and contains samples from novel classes outside the source domain. Source-free OSDA (SF-OSDA) techniques…

Unsupervised domain adaptation leverages abundant labeled data from various source domains to generalize onto unlabeled target data. Prior research has primarily focused on learning domain-invariant features across the source and target…

It is a strong prerequisite to access source data freely in many existing unsupervised domain adaptation approaches. However, source data is agnostic in many practical scenarios due to the constraints of expensive data transmission and data…

We address the Unsupervised Domain Adaptation (UDA) problem in image classification from a new perspective. In contrast to most existing works which either align the data distributions or learn domain-invariant features, we directly learn a…

Though vision transformers (ViTs) have exhibited impressive ability for representation learning, we empirically find that they cannot generalize well to unseen domains with previous domain generalization algorithms. In this paper, we…

Prior feature transformation based approaches to Unsupervised Domain Adaptation (UDA) employ the deep features extracted by pre-trained deep models without fine-tuning them on the specific source or target domain data for a particular…

Source-free domain adaptation in visual emotion recognition (SFDA-VER) is a highly challenging task that requires adapting VER models to the target domain without relying on source data, which is of great significance for data privacy…

Unsupervised domain adaptation (UDA) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain. Existing self-training based UDA approaches assign pseudo labels for target data and treat them as ground…

Existing learning-based methods for blind image quality assessment (BIQA) are heavily dependent on large amounts of annotated training data, and usually suffer from a severe performance degradation when encountering the domain/distribution…

Unsupervised domain adaptation (UDA) has become increasingly prevalent in scene text recognition (STR), especially where training and testing data reside in different domains. The efficacy of existing UDA approaches tends to degrade when…

Multi-source Domain Adaptation (MDA) aims to transfer predictive models from multiple, fully-labeled source domains to an unlabeled target domain. However, in many applications, relevant labeled source datasets may not be available, and…

Unsupervised domain adaptation (UDA) is the task of modifying a statistical model trained on labeled data from a source domain to achieve better performance on data from a target domain, with access to only unlabeled data in the target…

Existing Question Answering (QA) systems limited by the capability of answering questions from unseen domain or any out-of-domain distributions making them less reliable for deployment to real scenarios. Most importantly all the existing QA…

Deploying deep visual models can lead to performance drops due to the discrepancies between source and target distributions. Several approaches leverage labeled source data to estimate target domain accuracy, but accessing labeled source…