4 papers
Potential Energy based Mixture Model for Noisy Label Learning
Zijia Wang, Wenbin Yang, Zhisong Liu +1
Training deep neural networks (DNNs) from noisy labels is an important and challenging task. However, most existing approaches focus on the corrupted labels and ignore the importan…
Uncertainty-aware self-training with expectation maximization basis transformation
Zijia Wang, Wenbin Yang, Zhisong Liu +1
Self-training is a powerful approach to deep learning. The key process is to find a pseudo-label for modeling. However, previous self-training algorithms suffer from the over-confi…
Soft-IntroVAE for Continuous Latent space Image Super-Resolution
Zhi-Song Liu, Zijia Wang, Zhen Jia
Continuous image super-resolution (SR) recently receives a lot of attention from researchers, for its practical and flexible image scaling for various displays. Local implicit imag…
Arbitrary point cloud upsampling via Dual Back-Projection Network
Zhi-Song Liu, Zijia Wang, Zhen Jia
Point clouds acquired from 3D sensors are usually sparse and noisy. Point cloud upsampling is an approach to increase the density of the point cloud so that detailed geometric info…