Search Results for author:
Found 4 papers, 0 papers with code
Potential Energy based Mixture Model for Noisy Label Learning
Training deep neural networks (DNNs) from noisy labels is an important and challenging task.
Uncertainty-aware self-training with expectation maximization basis transformation
Specifically, we propose to use Expectation-Maximization (EM) to smooth the labels and comprehensively estimate the uncertainty information.
Soft-IntroVAE for Continuous Latent space Image Super-Resolution
Continuous image super-resolution (SR) recently receives a lot of attention from researchers, for its practical and flexible image scaling for various displays.
Arbitrary point cloud upsampling via Dual Back-Projection Network
Point cloud upsampling is an approach to increase the density of the point cloud so that detailed geometric information can be restored.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
