Results 21 to 30 of about 4,969,023 (298)
Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives [PDF]
APSIPA Transactions on Signal and Information Processing, 2022 Deep learning has become the method of choice to tackle real-world problems in different domains, partly because of its ability to learn from data and achieve impressive performance on a wide range of applications.
Xiaofeng Liu +6 more
semanticscholar +1 more source
Deep Hashing Network for Unsupervised Domain Adaptation [PDF]
Computer Vision and Pattern Recognition, 2017 In recent years, deep neural networks have emerged as a dominant machine learning tool for a wide variety of application domains. However, training a deep neural network requires a large amount of labeled data, which is an expensive process in terms of ...
Hemanth Venkateswara +3 more
semanticscholar +1 more source
Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering [PDF]
Transactions of the Association for Computational Linguistics, 2022 Retrieval Augment Generation (RAG) is a recent advancement in Open-Domain Question Answering (ODQA). RAG has only been trained and explored with a Wikipedia-based external knowledge base and is not optimized for use in other specialized domains such as ...
Shamane Siriwardhana +5 more
semanticscholar +1 more source
ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection [PDF]
Computer Vision and Pattern Recognition, 2021 We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised domain adaptation on 3D object detection from point clouds. First, we pre-train the 3D detector on the source domain with our proposed random object scaling strategy ...
Jihan Yang +4 more
semanticscholar +1 more source
Deep Visual Domain Adaptation: A Survey [PDF]
Neurocomputing, 2018 Deep domain adaption has emerged as a new learning technique to address the lack of massive amounts of labeled data. Compared to conventional methods, which learn shared feature subspaces or reuse important source instances with shallow representations ...
Mei Wang, Weihong Deng
semanticscholar +1 more source
OVANet: One-vs-All Network for Universal Domain Adaptation [PDF]
IEEE International Conference on Computer Vision, 2021 Universal Domain Adaptation (UNDA) aims to handle both domain-shift and category-shift between two datasets, where the main challenge is to transfer knowledge while rejecting "unknown" classes which are absent in the labeled source data but present in ...
Kuniaki Saito, Kate Saenko
semanticscholar +1 more source
FDDS: Feature Disentangling and Domain Shifting for Domain Adaptation
Mathematics, 2023 Domain adaptation is a learning strategy that aims to improve the performance of models in the current field by leveraging similar domain information. In order to analyze the effects of feature disentangling on domain adaptation and evaluate a model’s ...
Huan Chen, Farong Gao, Qizhong Zhang
doaj +1 more source
Maximum Classifier Discrepancy for Unsupervised Domain Adaptation [PDF]
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2017 In this work, we present a method for unsupervised domain adaptation. Many adversarial learning methods train domain classifier networks to distinguish the features as either a source or target and train a feature generator network to mimic the ...
Kuniaki Saito +3 more
semanticscholar +1 more source
FDA: Fourier Domain Adaptation for Semantic Segmentation [PDF]
Computer Vision and Pattern Recognition, 2020 We describe a simple method for unsupervised domain adaptation, whereby the discrepancy between the source and target distributions is reduced by swapping the low-frequency spectrum of one with the other. We illustrate the method in semantic segmentation,
Yanchao Yang, Stefano Soatto
semanticscholar +1 more source
Unsupervised Domain Adaptation via Domain-Adaptive Diffusion
, 2023 Unsupervised Domain Adaptation (UDA) is quite challenging due to the large distribution discrepancy between the source domain and the target domain. Inspired by diffusion models which have strong capability to gradually convert data distributions across a large gap, we consider to explore the diffusion technique to handle the challenging UDA task ...
Peng, Duo +3 more
openaire +2 more sources