Recent advances in variational autoencoders with representation learning for biomedical informatics: A survey
Variational autoencoders (VAEs) are deep latent space generative models that have been
immensely successful in multiple exciting applications in biomedical informatics such as …
immensely successful in multiple exciting applications in biomedical informatics such as …
A review of uncertainty quantification in medical image analysis: probabilistic and non-probabilistic methods
The comprehensive integration of machine learning healthcare models within clinical
practice remains suboptimal, notwithstanding the proliferation of high-performing solutions …
practice remains suboptimal, notwithstanding the proliferation of high-performing solutions …
An imbalanced binary classification method based on contrastive learning using multi-label confidence comparisons within sample-neighbors pair
X Gao, Z Meng, X Jia, J Liu, X Diao, B Xue, Z Huang… - Neurocomputing, 2023 - Elsevier
For imbalanced classification, data-level methods can achieve inter-class balance, but the
samples generated do not contain new information and cannot avoid the problem of …
samples generated do not contain new information and cannot avoid the problem of …
Speaker verification based on 3D variational self-coding multi-tasking adversarial network
H Liao, Y Xue - 2022 - researchsquare.com
In this paper, we leverage the generative adversarial mechanism and multi-task optimization
strategy to propose an architecture to enhance the accuracy of speaker verification. The …
strategy to propose an architecture to enhance the accuracy of speaker verification. The …