Related papers: Robust End-to-End Diarization with Domain Adaptive…
Domain adaptation is crucial in many real-world applications where the distribution of the training data differs from the distribution of the test data. Previous Deep Learning-based approaches to domain adaptation need to be trained jointly…
We propose associative domain adaptation, a novel technique for end-to-end domain adaptation with neural networks, the task of inferring class labels for an unlabeled target domain based on the statistical properties of a labeled source…
A practical shortcoming of deep neural networks is their specialization to a single task and domain. While recent techniques in domain adaptation and multi-domain learning enable the learning of more domain-agnostic features, their success…
We propose an extended framework for marginalized domain adaptation, aimed at addressing unsupervised, supervised and semi-supervised scenarios. We argue that the denoising principle should be extended to explicitly promote domain-invariant…
Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distribution, which may not…
Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions. We investigate the challenging problem of domain generalization, i.e., training a model on multi-domain source data…
Recent research efforts have shown that neural architectures can be effective in conventional information extraction tasks such as named entity recognition, yielding state-of-the-art results on standard newswire datasets. However, despite…
Large pre-trained models are usually fine-tuned on downstream task data, and tested on unseen data. When the train and test data come from different domains, the model is likely to struggle, as it is not adapted to the test domain. We…
Domain generalization aims to build generalized models that perform well on unseen domains when only source domains are available for model optimization. Recent studies have shown that large-scale pre-trained models can enhance domain…
Visual data driven dictionaries have been successfully employed for various object recognition and classification tasks. However, the task becomes more challenging if the training and test data are from contrasting domains. In this paper,…
The recent success of neural machine translation models relies on the availability of high quality, in-domain data. Domain adaptation is required when domain-specific data is scarce or nonexistent. Previous unsupervised domain adaptation…
While domain adaptation has been actively researched in recent years, most theoretical results and algorithms focus on the single-source-single-target adaptation setting. Naive application of such algorithms on multiple source domain…
Unsupervised domain adaptation has recently emerged as an effective paradigm for generalizing deep neural networks to new target domains. However, there is still enormous potential to be tapped to reach the fully supervised performance. In…
We are concerned with learning models that generalize well to different \emph{unseen} domains. We consider a worst-case formulation over data distributions that are near the source domain in the feature space. Only using training data from…
In Automatic Speech Recognition (ASR), teacher-student (T/S) training has shown to perform well for domain adaptation with small amount of training data. However, adaption without ground-truth labels is still challenging. A previous study…
The objective of unsupervised domain adaptation is to leverage features from a labeled source domain and learn a classifier for an unlabeled target domain, with a similar but different data distribution. Most deep learning approaches to…
The insertion of deep learning in medical image analysis had lead to the development of state-of-the art strategies in several applications such a disease classification, as well as abnormality detection and segmentation. However, even the…
Domain generalization involves learning a classifier from a heterogeneous collection of training sources such that it generalizes to data drawn from similar unknown target domains, with applications in large-scale learning and personalized…
The phenomenon of data distribution evolving over time has been observed in a range of applications, calling the needs of adaptive learning algorithms. We thus study the problem of supervised gradual domain adaptation, where labeled data…
Classical Domain Adaptation methods acquire transferability by regularizing the overall distributional discrepancies between features in the source domain (labeled) and features in the target domain (unlabeled). They often do not…