Results 21 to 30 of about 549,366 (277)
CROSS-DOMAIN TRANSFER OF DEFECT FEATURES IN TECHNICAL DOMAINS BASED ON PARTIAL TARGET DATA
International Journal of Prognostics and Health Management, 2023 A common challenge in real-world classification scenarios with sequentially appending target domain data is insufficient training datasets during the training phase.
Tobias Schlagenhauf, Tim Scheurenbrand
doaj +1 more source
Multi-Domain Feature Alignment for Face Anti-Spoofing
Sensors, 2023 Face anti-spoofing is critical for enhancing the robustness of face recognition systems against presentation attacks. Existing methods predominantly rely on binary classification tasks.
Shizhe Zhang, Wenhui Nie
doaj +1 more source
Neuron Coverage-Guided Domain Generalization
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023 This paper focuses on the domain generalization task where domain knowledge is unavailable, and even worse, only samples from a single domain can be utilized during training. Our motivation originates from the recent progresses in deep neural network (DNN) testing, which has shown that maximizing neuron coverage of DNN can help to explore possible ...
Chris Xing Tian +4 more
openaire +5 more sources
Barycentric-Alignment and Reconstruction Loss Minimization for Domain Generalization
IEEE Access, 2023 This paper advances the theory and practice of Domain Generalization (DG) in machine learning. We consider the typical DG setting where the hypothesis is composed of a representation mapping followed by a labeling function.
Boyang Lyu +4 more
doaj +1 more source
Information-theoretic analysis for transfer learning [PDF]
, 2020 Transfer learning, or domain adaptation, is concerned with machine learning problems in which training and testing data come from possibly different distributions (denoted as $\mu$ and $\mu'$, respectively). In this work, we give an information-theoretic
Aickelin, Uwe +3 more
core +2 more sources
Compactly generated domain theory [PDF]
Mathematical Structures in Computer Science, 2006 We propose compactly generated monotone convergence spaces as a well-behaved topological generalisation of directed-complete partial orders (dcpos). The category of such spaces enjoys the usual properties of categories of ‘predomains’ in denotational semantics.
Battenfeld, Ingo +2 more
openaire +2 more sources
Learning Robust Shape-Based Features for Domain Generalization
IEEE Access, 2020 Domain generalization is a challenging problem of learning models that can generalize to novel testing domains which are unavailable during training and follow different distributions from training domains.
Yexun Zhang +3 more
doaj +1 more source
Robust Place Categorization With Deep Domain Generalization [PDF]
, 2018 Traditional place categorization approaches in robot vision assume that training and test images have similar visual appearance. Therefore, any seasonal, illumination, and environmental changes typically lead to severe degradation in performance. To cope
Caputo, Barbara +3 more
core +2 more sources
Zero-Shot Domain Generalization
Proceedings of the British Machine Vision Conference 2020, 2020 Standard supervised learning setting assumes that training data and test data come from the same distribution (domain). Domain generalization (DG) methods try to learn a model that when trained on data from multiple domains, would generalize to a new unseen domain.
Maniyar, Udit +4 more
openaire +2 more sources
Domain Generalization by Marginal Transfer Learning
, 2020 In the problem of domain generalization (DG), there are labeled training data sets from several related prediction problems, and the goal is to make accurate predictions on future unlabeled data sets that are not known to the learner. This problem arises
Blanchard, Gilles +4 more
core +2 more sources