Search Results for author:
Found 10 papers, 4 papers with code
Discrete Prior-based Temporal-coherent Content Prediction for Blind Face Video Restoration
To further enhance the temporal coherence of the predicted content, a motion statistics modulation module is designed to adjust the content, based on discrete motion priors in terms of cross-frame mean and variance.
Learning Degradation-unaware Representation with Prior-based Latent Transformations for Blind Face Restoration
In this paper we present a Prior-based Latent Transformation approach (PLTrans) which is specifically designed to learn a degradation-unaware representation thereby allowing the restoration network to effectively generalize to real-world degradation.
VRetouchEr: Learning Cross-frame Feature Interdependence with Imperfection Flow for Face Retouching in Videos
Face Video Retouching is a complex task that often requires labor-intensive manual editing.
UFPS: A unified framework for partially-annotated federated segmentation in heterogeneous data distribution
We propose a Unified Federated Partially-labeled Segmentation (UFPS) framework to segment pixels within all classes for partially-annotated datasets by training a totipotential global model without class collision.
SPAC-Net: Synthetic Pose-aware Animal ControlNet for Enhanced Pose Estimation
Our work demonstrates the potential for synthetic data to overcome the challenge of limited annotated data in animal pose estimation.
TAP: Accelerating Large-Scale DNN Training Through Tensor Automatic Parallelisation
However, finding a suitable model parallel schedule for an arbitrary neural network is a non-trivial task due to the exploding search space.
Prior-Aware Synthetic Data to the Rescue: Animal Pose Estimation with Very Limited Real Data
Here, we present a very data efficient strategy targeted for pose estimation in quadrupeds that requires only a small amount of real images from the target animal.
M6-10T: A Sharing-Delinking Paradigm for Efficient Multi-Trillion Parameter Pretraining
Recent expeditious developments in deep learning algorithms, distributed training, and even hardware design for large models have enabled training extreme-scale models, say GPT-3 and Switch Transformer possessing hundreds of billions or even trillions of parameters.
M6-T: Exploring Sparse Expert Models and Beyond
Mixture-of-Experts (MoE) models can achieve promising results with outrageous large amount of parameters but constant computation cost, and thus it has become a trend in model scaling.
M6: A Chinese Multimodal Pretrainer
In this work, we construct the largest dataset for multimodal pretraining in Chinese, which consists of over 1. 9TB images and 292GB texts that cover a wide range of domains.
