Results 11 to 20 of about 234,412 (208)
ViT-AE++: Improving Vision Transformer Autoencoder for Self-supervised Medical Image Representations [PDF]
CoRR, 2023 Self-supervised learning has attracted increasing attention as it learns data-driven representation from data without annotations. Vision transformer-based autoencoder (ViT-AE) by He et al. (2021) is a recent self-supervised learning technique that employs a patch-masking strategy to learn a meaningful latent space. In this paper, we focus on improving
Prabhakar, Chinmay +5 more
core +6 more sources
AE-MoSE: an AutoEncoder Mixture of Spatial Experts for Geodemographic Classification
This work introduces a novel approach to geodemographic classification that combines an AutoEncoder architecture with a Mixture of Experts framework, incorporating a Graph Neural Network into the gating component to create a Mixture of Spatial Experts approach (AE-MoSE).
De Sabbata, Stef +3 more
core +8 more sources
WOT-AE: Weighted Optimal Transport Autoencoder for Patterned Fabric Defect Detection
SymmetryPatterned fabrics are characterized by strong periodic and symmetric structures, and defect detection in such materials is essentially the task of identifying local disruptions of global texture symmetry. Conventional low-rank decomposition methods separate defect-free regions as low-rank and defects as sparse components, yet singular value ...
Hui Yang, Linyan Kang, Tianjin Yang
openaire +2 more sources
IEEE Transactions on Geoscience and Remote SensingSpectral unmixing has been extensively studied with a variety of methods and used in many applications. Recently, data-driven techniques with deep learning methods have obtained great attention to spectral unmixing for its superior learning ability to automatically learn the structure information.
Min Zhao 0014 +2 more
openaire +5 more sources
DSFC-AE: A New Hyperspectral Unmixing Method Based on Deep Shared Fully Connected Autoencoder
IEEE Journal of Selected Topics in Applied Earth Observations and Remote SensingThe pervasive presence of mixed pixels in hyperspectral remote sensing imagery poses a substantial constraint on the quantitative progress of remote sensing technology. Hyperspectral unmixing (HU) techniques serve as effective means to address this issue.
Hao Chen 0192 +4 more
openaire +3 more sources
Credit Card Fraud Detection with Autoencoder and Probabilistic Random Forest
Mathematics, 2021 This paper proposes a method, called autoencoder with probabilistic random forest (AE-PRF), for detecting credit card frauds. The proposed AE-PRF method first utilizes the autoencoder to extract features of low-dimensionality from credit card transaction
Tzu-Hsuan Lin, Jehn-Ruey Jiang
doaj +1 more source
An individualization approach for head-related transfer function in arbitrary directions based on deep learning [PDF]
JASA Express Letters, 2022 This paper provides an individualization approach for head-related transfer function (HRTF) in arbitrary directions based on deep learning by utilizing dual-autoencoder architecture to establish the relationship between HRTF magnitude spectrum and ...
Dingding Yao +6 more
doaj +1 more source
Idea of AE separation from unpredicted source area during AE testing by autoencoder [PDF]
Proceedings of 1st International Electronic Conference on Applied Sciences, 2020 When conducting AE testing, there is an industrial need to separate AE from monitoring area to that from outside of the area in some cases. In this study, usefulness of autoencoder to solve this problem is discussed by simple experiment using an isotropic thin steel ruler.
openaire +1 more source
Linear local tangent space alignment with autoencoder
Complex & Intelligent Systems, 2023 Linear local tangent space alignment (LLTSA) is a classical dimensionality reduction method based on manifold. However, LLTSA and all its variants only consider the one-way mapping from high-dimensional space to low-dimensional space.
Ruisheng Ran, Jinping Wang, Bin Fang
doaj +1 more source