9 citations · 28 across the 8 of their papers we have counts for
11 papers
Multi-stage feature decorrelation constraints for improving CNN classification performance
Qiuyu Zhu, Hao Wang, Xuewen Zu +1
For the convolutional neural network (CNN) used for pattern classification, the training loss function is usually applied to the final output of the network, except for some regula…
Effective Out-of-Distribution Detection in Classifier Based on PEDCC-Loss
Qiuyu Zhu, Guohui Zheng, Yingying Yan
Deep neural networks suffer from the overconfidence issue in the open world, meaning that classifiers could yield confident, incorrect predictions for out-of-distribution (OOD) sam…
A Softmax-free Loss Function Based on Predefined Optimal-distribution of Latent Features for Deep Learning Classifier
Qiuyu Zhu, Xuewen Zu
In the field of pattern classification, the training of deep learning classifiers is mostly end-to-end learning, and the loss function is the constraint on the final output (poster…
Single Underwater Image Enhancement Using an Analysis-Synthesis Network
Zhengyong Wang, Liquan Shen, Mei Yu +2
Most deep models for underwater image enhancement resort to training on synthetic datasets based on underwater image formation models. Although promising performances have been ach…
Generation and frame characteristics of predefined evenly-distributed class centroids for pattern classification
Haiping Hu, Yingying Yan, Qiuyu Zhu +1
Predefined evenly-distributed class centroids (PEDCC) can be widely used in models and algorithms of pattern classification, such as CNN classifiers, classification autoencoders, c…
Semi-supervised learning method based on predefined evenly-distributed class centroids
Qiuyu Zhu, Tiantian Li
Compared to supervised learning, semi-supervised learning reduces the dependence of deep learning on a large number of labeled samples. In this work, we use a small number of label…