Results 21 to 30 of about 482,653 (299)
Feature Selection for Transfer Learning [PDF]
, 2011 Common assumption in most machine learning algorithms is that, labeled (source) data and unlabeled (target) data are sampled from the same distribution. However, many real world tasks violate this assumption: in temporal domains, feature distributions may vary over time, clinical studies may have sampling bias, or sometimes sufficient labeled data for ...
Selen Uguroglu, Jaime G. Carbonell
openaire +1 more source
Transfer Learning for Feature Dimensionality Reduction
The International Arab Journal of Information Technology, 2022 Transfer learning is a machine learning methodology by which a model developed for achieving a task is exploited for another related job. Many pre-trained image classification models trained on ImageNet are used for transfer learning. These pre-trained networks could also be used for classifying out of domain images by retraining them.
Nikhila Thribhuvan, Sudheep Elayidom
openaire +1 more source
Feature Map Regularized CycleGAN for Domain Transfer
Mathematics, 2023 CycleGAN domain transfer architectures use cycle consistency loss mechanisms to enforce the bijectivity of highly underconstrained domain transfer mapping.
Lidija Krstanović +3 more
doaj +1 more source
Feature Space Transfer for Data Augmentation [PDF]
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018 The problem of data augmentation in feature space is considered. A new architecture, denoted the FeATure TransfEr Network (FATTEN), is proposed for the modeling of feature trajectories induced by variations of object pose. This architecture exploits a parametrization of the pose manifold in terms of pose and appearance.
Bo Liu 0043 +4 more
openaire +2 more sources
Transferable Perturbations of Deep Feature Distributions
CoRR, 2020 Published as a conference paper at ICLR ...
Nathan Inkawhich +3 more
openaire +3 more sources
Feature Spaces-based Transfer Learning [PDF]
Advances in Intelligent Systems Research, 2015 Transfer learning provides an approach to solve target tasks more quickly and effectively by using previouslyacquired knowledge learned from source tasks. Most of transfer learning approaches extract knowledge of source domain in the given feature space. The issue is that single perspective can‟t mine the relationship of source domain and target domain
Hua Zuo +3 more
openaire +1 more source
Algorithm of Stability-Analysis-Based Feature Selection for NIR Calibration Transfer
Sensors, 2022 For conventional near-infrared spectroscopy (NIR) technology, even within the same sample, the NIR spectral signal can vary significantly with variation of spectrometers and the spectral collection environment.
Zheyu Zhang +4 more
doaj +1 more source
CoRR, 2019 Under difficult environmental conditions, the view of RGB cameras may be restricted by fog, dust or difficult lighting situations. Because thermal cameras visualize thermal radiation, they are not subject to the same limitations as RGB cameras. However, because RGB and thermal imaging differ significantly in appearance, common, state-of-the-art feature
Sebastian P. Kleinschmidt +1 more
openaire +2 more sources
Feature-Based Transfer Learning Based on Distribution Similarity
IEEE Access, 2018 Transfer learning has been found helpful at enhancing the target domain's learning process by transferring useful knowledge from other different but related source domains.
Xiaofeng Zhong +5 more
doaj +1 more source