For the convolutional neural network (CNN) used for pattern classificati...
Deep neural networks suffer from the overconfidence issue in the open wo...
Most deep models for underwater image enhancement resort to training on
...
Predefined evenly-distributed class centroids (PEDCC) can be widely used...
The multi-armed bandit (MAB) problem is a ubiquitous decision-making pro...
The multi-armed bandit (MAB) problem is a classical learning task that
e...
Compared to supervised learning, semi-supervised learning reduces the
de...
The main purpose of incremental learning is to learn new knowledge while...
In this paper, we propose an end-to-end image clustering auto-encoder
al...
With the development of convolutional neural networks (CNNs) in recent y...
Classic Autoencoders and variational autoencoders are used to learn comp...
In order to enhance the real-time performance of convolutional neural
ne...