More is Better: Deep Domain Adaptation with Multiple Sources
In many practical applications, it is often difficult and expensive to obtain large-scale labeled data to train state-of-the-art deep neural networks. Therefore, transferring the learned knowledge from a separate, labeled source domain to an unlabeled or sparsely labeled target domain becomes an appealing alternative. However, direct transfer often results in significant performance decay due to domain shift. Domain adaptation (DA) aims to address this problem by aligning the distributions between the source and target domains. Multi-source domain adaptation (MDA) is a powerful and practical extension in which the labeled data may be collected from multiple sources with different distributions. In this survey, we first define various MDA strategies. Then we systematically summarize and compare modern MDA methods in the deep learning era from different perspectives, followed by commonly used datasets and a brief benchmark. Finally, we discuss future research directions for MDA that are worth investigating.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationSimilar Papers 제목 키워드 기반
Robust Multi-Source Domain Adaptation under Label Shift
As the volume of data continues to expand, it becomes increasingly common for data to be aggregated from multiple sources. Leveraging multiple sources for model training typically achieves better predictive performance o…
Domain AdaptationOutlier DetectionAggregating From Multiple Target-Shifted Sources
Multi-source domain adaptation aims at leveraging the knowledge from multiple tasks for predicting a related target domain. Hence, a crucial aspect is to properly combine different sources based on their relations. In th…
Domain AdaptationUnsupervised Domain AdaptationA Multi-Discriminator CycleGAN for Unsupervised Non-Parallel Speech Domain Adaptation
Domain adaptation plays an important role for speech recognition models, in particular, for domains that have low resources. We propose a novel generative model based on cyclic-consistent generative adversarial network (…
Domain AdaptationGenerative Adversarial Networkspeech-recognitionSpeech RecognitionDynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domains
Few-shot domain adaptation to multiple domains aims to learn a complex image distribution across multiple domains from a few training images. A na\"ive solution here is to train a separate model for each domain using few…
Domain AdaptationTensor DecompositionDeep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift
Unsupervised domain adaptation (UDA) conventionally assumes labeled source samples coming from a single underlying source distribution. Whereas in practical scenario, labeled data are typically collected from diverse sou…
Domain AdaptationMulti-Source Unsupervised Domain AdaptationUnsupervised Domain Adaptation