Výsledky vyhledávání - class-specific deep autoencoder*

Sample reconstruction with deep autoencoder for one sample per person face recognition Autor Zhang, Yan, Peng, Hua

“… In the proposed algorithm, a generalised deep autoencoder is first trained with all images in the gallery, then a class-specific deep autoencoder (CDA…”
Získat plný text

Enhanced prediction of recombination hotspots using input features extracted by class specific autoencoders Autor Nath, Abhigyan, Karthikeyan, S.

“…•Combination of class specific autoencoders. In yeast and in some mammals the frequencies of recombination are high in some genomic locations which are known as recombination hotspots and in the locations where the recombination is below…”
Získat plný text

Are you eligible? Predicting adulthood from face images via Class Specific Mean Autoencoder Autor Singh, Maneet, Nagpal, Shruti, Vatsa, Mayank, Singh, Richa

“…•Proposed Class Specific Mean Autoencoder for learning class representative features…”
Získat plný text

Supervised Mixed Norm Autoencoder for Kinship Verification in Unconstrained Videos Autor Kohli, Naman, Yadav, Daksha, Vatsa, Mayank, Singh, Richa, Noore, Afzel

“…). This new autoencoder formulation introduces class-specific sparsity in the weight matrix…”
Získat plný text

Online Bengali handwritten numerals recognition using Deep Autoencoders Autor Pal, Arghya, Khonglah, B. K., Mandal, S., Choudhury, Himakshi, Prasanna, S. R. M., Rufiner, H. L., Balasubramanian, Vineeth N.

“…) based on Multilayer perceptron (MLP) [1]. Autoencoders capture the class specific information and the deep version uses many hidden layers and a final classification layer to accomplish…”
Získat plný text

Two-Stream Deep Architecture for Hyperspectral Image Classification Autor Hao, Siyuan, Wang, Wei, Ye, Yuanxin, Nie, Tingyuan, Bruzzone, Lorenzo

“… In order to effectively exploit and fuse both the spatial context and spectral structure, we propose a novel two-stream deep architecture for HSI classification…”
Získat plný text

Class-specific pre-trained sparse autoencoders for learning effective features for document classification Autor Abdulhussain, Maysa I., Gan, John Q.

“… (unsupervised feature learning). This paper proposes class-specific (supervised) pre-trained approach based on sparse autoencoder to gain low-dimensional interesting structure of features with high performance in document classification…”
Získat plný text

Are you eligible? Predicting adulthood from face images via class specific mean autoencoder Autor Singh, Maneet, Nagpal, Shruti, Vatsa, Mayank, Singh, Richa

“… This paper presents a novel deep learning based formulation, termed as Class Specific Mean Autoencoder, to learn the intra-class similarity and extract class-specific features…”
Získat plný text

Data-driven deep learning approach for suggesting process parameters for the milling operations Autor Asghar, Eram, Ratti, Andrea, Tolio, Tullio

“…This work introduces an approach that leverages neural networks to classify 3D models based on volumetric boundaries and systematically organizes machining…”
Získat plný text

A unified framework incorporating predictive generative denoising autoencoder and deep Coral network for rolling bearing fault diagnosis with unbalanced data Autor Li, Xingqiu, Jiang, Hongkai, Liu, Shaowei, Zhang, Jianjun, Xu, Jun

“…•A unified framework is proposed for fault diagnosis with unbalanced data.•Predictive generative denoising autoencoder is developed for data generating…”
Získat plný text

Two-Phase Multitask Autoencoder-Based Deep Learning Framework for Subject-Independent EEG Motor Imagery Classification Autor Jin, Changgyun, Song, Andrew H., Kim, Seong-Eun

“… Our framework comprises two phases: first, the generation of a class-specific target signal…”
Získat plný text

Using convolutional features and a sparse autoencoder for land-use scene classification Autor Othman, Esam, Bazi, Yakoub, Alajlan, Naif, Alhichri, Haikel, Melgani, Farid

“…In this article, we propose a novel approach based on convolutional features and sparse autoencoder (AE…”
Získat plný text

FARMSAR: Fixing AgRicultural Mislabels Using Sentinel-1 Time Series and AutoencodeRs Autor Di Martino, Thomas, Guinvarc’h, Régis, Thirion-Lefevre, Laetitia, Colin, Elise

“… To process and correct these errors, we design a two-step methodology. Using class-specific convolutional autoencoders applied to synthetic aperture radar (SAR…”
Získat plný text

BSCGAN: structured minority class image generation under class-balanced pretraining Autor Wan, Qian, Zhou, Bin, Wang, Yanjiang

“… Generative adversarial minority oversampling (GAMO) and deep synthetic minority oversampling technique (SMOTE…”
Získat plný text

BOSC: A Backdoor-Based Framework for Open Set Synthetic Image Attribution Autor Wang, Jun, Tondi, Benedetta, Barni, Mauro

“…With the continuous progress of AI technology, new generative architectures continuously appear, thus driving the attention of researchers towards the…”
Získat plný text

DDoS attack detection in smart grid network using reconstructive machine learning models Autor Naqvi, Sardar Shan Ali, Li, Yuancheng, Uzair, Muhammad

“…Network attacks pose a significant challenge for smart grid networks, mainly due to the existence of several multi-directional communication devices coupling…”
Získat plný text

Gene set inference from single-cell sequencing data using a hybrid of matrix factorization and variational autoencoders Autor Lukassen, Soeren, Ten, Foo Wei, Adam, Lukas, Eils, Roland, Conrad, Christian

“… Here, we propose a deep neural network model that is a hybrid of matrix factorization and variational autoencoders, which we call restricted latent variational autoencoder (resVAE…”
Získat plný text

GAN-MVAE: A discriminative latent feature generation framework for generalized zero-shot learning Autor Ma, Peirong, Lu, Hong, Yang, Bohong, Ran, Wu

“… GAN can generate missing unseen classes samples from class-specific semantic embedding…”
Získat plný text

Integrated damage detection and time-series data augmentation for floating offshore mooring systems via variational semi-supervised learning Autor Tamuly, Pranjal, Sharma, Smriti, Nava, Vincenzo

“…•The performance surpasses that of other deep learning models when working with limited labelled data…”
Získat plný text

One-Class Adversarial Fraud Detection Nets with Class Specific Representations Autor Peng, Haipeng, Zhao, Jie, Li, Lixiang, Ren, Yeqing, Zhao, Shanshan

“… This paper proposes a new one-class classification model called one-class adversarial fraud detection nets with class specific representations (CS-OCAN…”
Získat plný text