Search Results for author:
Found 9 papers, 6 papers with code
Enhancing Mixup-based Semi-Supervised Learning with Explicit Lipschitz Regularization
On three benchmark data sets and one real-world biomedical data set, we demonstrate that this combined regularization results in improved generalization performance of SSL when learning from a small amount of labeled data.
Learning Geometry-Dependent and Physics-Based Inverse Image Reconstruction
However, many reconstruction problems involve imaging physics that are dependent on the underlying non-Euclidean geometry.
Semi-supervised Medical Image Classification with Global Latent Mixing
In this work, we argue that regularizing the global smoothness of neural functions by filling the void in between data points can further improve SSL.
Progressive Learning and Disentanglement of Hierarchical Representations
By drawing on the respective advantage of hierarchical representation learning and progressive learning, this is to our knowledge the first attempt to improve disentanglement by progressively growing the capacity of VAE to learn hierarchical representations.
Improving Disentangled Representation Learning with the Beta Bernoulli Process
We note that the independence within and the complexity of the latent density are two different properties we constrain when regularizing the posterior density: while the former promotes the disentangling ability of VAE, the latter -- if overly limited -- creates an unnecessary competition with the data reconstruction objective in VAE.
Semi-Supervised Learning by Disentangling and Self-Ensembling Over Stochastic Latent Space
In this work, we hypothesize -- from the generalization perspective -- that self-ensembling can be improved by exploiting the stochasticity of a disentangled latent space.
Generative Modeling and Inverse Imaging of Cardiac Transmembrane Potential
We introduce a novel model-constrained inference framework that replaces conventional physiological models with a deep generative model trained to generate TMP sequences from low-dimensional generative factors.
Improving Generalization of Deep Networks for Inverse Reconstruction of Image Sequences
Deep learning networks have shown state-of-the-art performance in many image reconstruction problems.
Improving Generalization of Sequence Encoder-Decoder Networks for Inverse Imaging of Cardiac Transmembrane Potential
The results demonstrate that the generalization ability of an inverse reconstruction network can be improved by constrained stochasticity combined with global aggregation of temporal information in the latent space.
