scholar.google.com › citations
In this work, we use an oversampling method that leverages information in both the majority and minority classes to mitigate the class imbalance problem.
In this work, we proposed a generative oversampling method based on a contrastive variational autoencoder. Instead of using only the observed minority ...
Nov 1, 2019 · In this work, we use an oversampling method that leverages information in both the majority and minority classes to mitigate the class imbalance ...
In this work, we use an oversampling method that leverages information in both the majority and minority classes to mitigate the class imbalance problem.
Experimental results on two clinical datasets with highly imbalanced outcomes demonstrate that prediction models can be significantly improved using data ...
Feb 26, 2020 · In this work, we use an oversampling method that leverages information in both the majority and minority classes to mitigate the class imbalance ...
Jun 26, 2023 · Bibliographic details on Generative Oversampling with a Contrastive Variational Autoencoder.
People also ask
Are variational autoencoders generative?
What is the primary goal of a variational autoencoder (VAE) in generative AI?
What's the difference between a variational autoencoder VAE and an autoencoder?
What is the use case of variational autoencoder?
Feb 14, 2023 · Learning with imbalanced data is a challenging problem in deep learning. Over-sampling is a widely used technique to re-balance the sampling.
May 1, 2021 · Deep conditional generative models can improve accuracy in imbalanced learning. Variational Autoencoders achieve better results than Generative Adversarial ...
Missing: Contrastive | Show results with:Contrastive
A novel over-sampling model, called Majority-Guided VAE~(MGVAE), which generates new minority samples under the guidance of a majority-based prior.