Bharat Subedi - Academia.edu (original) (raw)

Related Authors

Omid Poursaeed

Ali Borji

Nasik Muhammad Nafi

aanchal sahu

Kalinga Institute of Industrial Technology (KIIT)

Kai Keng Ang

Jung-Woo Ha

Jeremiah Deng

Uploads

Papers by Bharat Subedi

Research paper thumbnail of Feature Learning-Based Generative Adversarial Network Data Augmentation for Class-Based Few-Shot Learning

Mathematical Problems in Engineering

As training deep neural networks enough requires a large amount of data, there have been a lot of... more As training deep neural networks enough requires a large amount of data, there have been a lot of studies to deal with this problem. Data augmentation techniques are basic solutions to increase training data using existing data. Geometric transformations and color space augmentations are well-known augmentation techniques, but they still require some manual work and can generate limited types of data only. Therefore, there are many interests in generative-model-based augmentation lately, which can learn the distribution of data. This study proposes a set of GAN-based data augmentation methods that can generate good quality training data. The proposed networks, f-DAGAN (data augmentation generative adversarial networks), have been motivated by the DAGAN that learns data distribution from two real data. The basic f-DAGAN uses dual discriminators handling both generated data and generated feature spaces for better learning the given data. The other versions of f-DAGANs have been propos...

Research paper thumbnail of Rice leaf diseases prediction using deep neural networks with transfer learning

Research paper thumbnail of Development of a Low-cost Industrial OCR System with an End-to-end Deep Learning Technology

Research paper thumbnail of A Comprehensive Review on Secure Data Sharing in Cloud Environment

Wireless Personal Communications

Research paper thumbnail of Feature Learning-Based Generative Adversarial Network Data Augmentation for Class-Based Few-Shot Learning

Mathematical Problems in Engineering

As training deep neural networks enough requires a large amount of data, there have been a lot of... more As training deep neural networks enough requires a large amount of data, there have been a lot of studies to deal with this problem. Data augmentation techniques are basic solutions to increase training data using existing data. Geometric transformations and color space augmentations are well-known augmentation techniques, but they still require some manual work and can generate limited types of data only. Therefore, there are many interests in generative-model-based augmentation lately, which can learn the distribution of data. This study proposes a set of GAN-based data augmentation methods that can generate good quality training data. The proposed networks, f-DAGAN (data augmentation generative adversarial networks), have been motivated by the DAGAN that learns data distribution from two real data. The basic f-DAGAN uses dual discriminators handling both generated data and generated feature spaces for better learning the given data. The other versions of f-DAGANs have been propos...

Research paper thumbnail of Rice leaf diseases prediction using deep neural networks with transfer learning

Research paper thumbnail of Development of a Low-cost Industrial OCR System with an End-to-end Deep Learning Technology

Research paper thumbnail of A Comprehensive Review on Secure Data Sharing in Cloud Environment

Wireless Personal Communications

Log In