research
∙
08/24/2023
Multi-stage feature decorrelation constraints for improving CNN classification performance
For the convolutional neural network (CNN) used for pattern classificati...
share
research
∙
04/10/2022
Effective Out-of-Distribution Detection in Classifier Based on PEDCC-Loss
Deep neural networks suffer from the overconfidence issue in the open wo...
research
∙
08/20/2021
Single Underwater Image Enhancement Using an Analysis-Synthesis Network
Most deep models for underwater image enhancement resort to training on ...
research
∙
05/02/2021
Generation and frame characteristics of predefined evenly-distributed class centroids for pattern classification
Predefined evenly-distributed class centroids (PEDCC) can be widely used...
research
∙
11/16/2020
Risk-Constrained Thompson Sampling for CVaR Bandits
The multi-armed bandit (MAB) problem is a ubiquitous decision-making pro...
research
∙
02/01/2020
Thompson Sampling Algorithms for Mean-Variance Bandits
The multi-armed bandit (MAB) problem is a classical learning task that e...
research
∙
01/13/2020
Semi-supervised learning method based on predefined evenly-distributed class centroids
Compared to supervised learning, semi-supervised learning reduces the de...
research
∙
06/11/2019
Incremental Classifier Learning Based on PEDCC-Loss and Cosine Distance
The main purpose of incremental learning is to learn new knowledge while...
research
∙
06/10/2019
An Image Clustering Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids and MMD Distance
In this paper, we propose an end-to-end image clustering auto-encoder al...
research
∙
04/12/2019
A New Loss Function for CNN Classifier Based on Pre-defined Evenly-Distributed Class Centroids
With the development of convolutional neural networks (CNNs) in recent y...
research
∙
02/01/2019
A Classification Supervised Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids
Classic Autoencoders and variational autoencoders are used to learn comp...
research
∙
03/07/2018