Search Results for author:
Found 8 papers, 3 papers with code
Rotating Your Face Using Multi-Task Deep Neural Network
This paper proposes a new deep architecture based on a novel type of multitask learning, which can achieve superior performance in rotating to a target-pose face image from an arbitrary pose and illumination image while preserving identity.
Joint Fine-Tuning in Deep Neural Networks for Facial Expression Recognition
Furthermore, we show that our new integration method gives more accurate results than traditional methods, such as a weighted summation and a feature concatenation method.
Facial Expression Recognition
Facial Expression Recognition (FER)
A Gift From Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning
We introduce a novel technique for knowledge transfer, where knowledge from a pretrained deep neural network (DNN) is distilled and transferred to another DNN.
NLNL: Negative Learning for Noisy Labels
The classical method of training CNNs is by labeling images in a supervised manner as in "input image belongs to this label" (Positive Learning; PL), which is a fast and accurate method if the labels are assigned correctly to all images.
Highway Driving Dataset for Semantic Video Segmentation
Together with our attempt to analyze the temporal correlation, we expect the Highway Driving dataset to encourage research on semantic video segmentation.
Confidence Score Weighting Adaptation for Source-Free Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) aims to achieve high performance within the unlabeled target domain by leveraging the labeled source domain.
Hyperparameter Optimization with Neural Network Pruning
However, the huge time consumption of hyperparameter optimization due to the high computational cost of the deep learning model itself has not been dealt with in-depth.
Confidence Score for Source-Free Unsupervised Domain Adaptation
Unlike existing confidence scores that use only one of the source or target domain knowledge, the JMDS score uses both knowledge.
