Results 71 to 80 of about 8,068,927 (352)
: Most of the existing research on unsupervised cross-domain intelligent fault diagnosis is based on single-source domain adaptation, which fails to simultaneously utilize various source domains with enough and diverse diagnostic information in practical
Xingkai Chen +5 more
semanticscholar +1 more source
Domain adaptation by topology regularization [PDF]
Deep learning has become the leading approach to assisted target recognition. While these methods typically require large amounts of labeled training data, domain adaptation (DA) or transfer learning (TL) enables these algorithms to transfer knowledge from a labelled (source) data set to an unlabelled but related (target) data set of interest.
Deborah Weeks, Samuel Rivera
openaire +3 more sources
Discriminativeness-Preserved Domain Adaptation for Few-Shot Learning
Existing few-shot learning (FSL) methods make the implicit assumption that the few target class samples are from the same domain as the source class samples.
Guangzhen Liu, Zhiwu Lu
doaj +1 more source
Reciprocal normalization for domain adaptation
Batch normalization (BN) is widely used in modern deep neural networks, which has been shown to represent the domain-related knowledge, and thus is ineffective for cross-domain tasks like unsupervised domain adaptation (UDA). Existing BN variant methods aggregate source and target domain knowledge in the same channel in normalization module.
Zhiyong Huang 0009 +7 more
openaire +3 more sources
Topic modeling-based domain adaptation for system combination [PDF]
This paper gives the system description of the domain adaptation team of Dublin City University for our participation in the system combination task in the Second Workshop on Applying Machine Learning Techniques to Optimise the Division of Labour in ...
Okita, Tsuyoshi +2 more
core +2 more sources
Return of Frustratingly Easy Domain Adaptation [PDF]
Unlike human learning, machine learning often fails to handle changes between training (source) and test (target) input distributions. Such domain shifts, common in practical scenarios, severely damage the performance of conventional machine learning
Baochen Sun, Jiashi Feng, Kate Saenko
semanticscholar +1 more source
Unsupervised Domain Adaptation with Semantic Consistency across Heterogeneous Modalities for MRI Prostate Lesion Segmentation [PDF]
Any novel medical imaging modality that differs from previous protocols e.g. in the number of imaging channels, introduces a new domain that is heterogeneous from previous ones.
Chiou, E +4 more
core +1 more source
Combining multi-domain statistical machine translation models using automatic classifiers [PDF]
This paper presents a set of experiments on Domain Adaptation of Statistical Machine Translation systems. The experiments focus on Chinese-English and two domain-specific corpora. The paper presents a novel approach for combining multiple domain-trained
Li, Baoli +5 more
core +2 more sources
Standard supervised machine learning assumes that the distribution of the source samples used to train an algorithm is the same as the one of the target samples on which it is supposed to make predictions. However, as any data scientist will confirm, this is hardly ever the case in practice.
Pirmin Lemberger, Ivan Panico
openaire +3 more sources
Meta Domain Adaptation Approach for Multi-Domain Ranking
In a real industry recommendation system, the distribution of recommended domains is very redundant. Different domains may address the same problem, such as the Click-Through Rate (CTR) prediction, and may share the same features.
Zihan Xia +4 more
doaj +1 more source

