Generative Oversampling for Imbalanced Data via Majority-Guided VAE

no code implementations • 14 Feb 2023 • Qingzhong Ai, Pengyun Wang, Lirong He, Liangjian Wen, Lujia Pan, Zenglin Xu

Learning with imbalanced data is a challenging problem in deep learning.

A One-Shot Reparameterization Method for Reducing the Loss of Tile Pruning on DNNs

1 code implementation • 29 Jul 2022 • Yanchen Li, Qingzhong Ai, Fumihiko Ino

In this study, we propose a one-shot reparameterization method, called TileTrans, to reduce the loss of tile pruning.

ByPE-VAE: Bayesian Pseudocoresets Exemplar VAE

1 code implementation • NeurIPS 2021 • Qingzhong Ai, Lirong He, Shiyu Liu, Zenglin Xu

To address this issue, we propose Bayesian Pseudocoresets Exemplar VAE (ByPE-VAE), a new variant of VAE with a prior based on Bayesian pseudocoreset.

Data Augmentation Density Estimation +2

Stein Variational Gradient Descent with Multiple Kernel

no code implementations • 20 Jul 2021 • Qingzhong Ai, Shiyu Liu, Lirong He, Zenglin Xu

In practice, we notice that the kernel used in SVGD-based methods has a decisive effect on the empirical performance.

Computational Efficiency