23 citations · 67 across the 11 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…
Incremental Classifier Learning Based on PEDCC-Loss and Cosine Distance
Qiuyu Zhu, Zikuang He, Xin Ye
The main purpose of incremental learning is to learn new knowledge while not forgetting the knowledge which have been learned before. At present, the main challenge in this area is…
An Image Clustering Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids and MMD Distance
Qiuyu Zhu, Zhengyong Wang
In this paper, we propose a novel, effective and simpler end-to-end image clustering auto-encoder algorithm: ICAE. The algorithm uses PEDCC (Predefined Evenly-Distributed Class Cen…
A New Loss Function for CNN Classifier Based on Pre-defined Evenly-Distributed Class Centroids
Qiuyu Zhu, Pengju Zhang, Xin Ye
With the development of convolutional neural networks (CNNs) in recent years, the network structure has become more and more complex and varied, and has achieved very good results…
A Classification Supervised Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids
Qiuyu Zhu, Ruixin Zhang
Classic variational autoencoders are used to learn complex data distributions, that are built on standard function approximators. Especially, VAE has shown promise on a lot of comp…
HENet:A Highly Efficient Convolutional Neural Networks Optimized for Accuracy, Speed and Storage
Qiuyu Zhu, Ruixin Zhang
In order to enhance the real-time performance of convolutional neural networks(CNNs), more and more researchers are focusing on improving the efficiency of CNN. Based on the analys…