Search Results for author:
Found 8 papers, 2 papers with code
Label-Noise Robust Domain Adaptation
Domain adaptation aims to correct the classifiers when faced with distribution shift between source (training) and target (test) domains.
FaceController: Controllable Attribute Editing for Face in the Wild
By simply employing some existing and easy-obtainable prior information, our method can control, transfer, and edit diverse attributes of faces in the wild.
Ranked #1 on
Face Swapping
on FaceForensics++
(FID metric)
NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results
This challenge is based on a newly collected validation and testing image datasets, and hence, named SIDD+.
An Efficient and Provable Approach for Mixture Proportion Estimation Using Linear Independence Assumption
In this paper, we study the mixture proportion estimation (MPE) problem in a new setting: given samples from the mixture and the component distributions, we identify the proportions of the components in the mixture distribution.
Learning with Biased Complementary Labels
We therefore reason that the transition probabilities will be different.
Transfer Learning with Label Noise
However, when learning this invariant knowledge, existing methods assume that the labels in source domain are uncontaminated, while in reality, we often have access to source data with noisy labels.
On Compressing Deep Models by Low Rank and Sparse Decomposition
Deep compression refers to removing the redundancy of parameters and feature maps for deep learning models.
Variance-Reduced Proximal Stochastic Gradient Descent for Non-convex Composite optimization
To the best of our knowledge, this is the first analysis of convergence rate of variance-reduced proximal stochastic gradient for non-convex composite optimization.
