144 citations · 1.1k across the 52 of their papers we have counts for
13 papers · 1 filter
Imitation Learning from Purified Demonstrations
Yunke Wang, Minjing Dong, Yukun Zhao +2
Imitation learning has emerged as a promising approach for addressing sequential decision-making problems, with the assumption that expert demonstrations are optimal. However, in r…
A Benchmark Study on Calibration
Linwei Tao, Younan Zhu, Haolan Guo +2
Deep neural networks are increasingly utilized in various machine learning tasks. However, as these models grow in complexity, they often face calibration issues, despite enhanced…
Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning
Yunke Wang, Bo Du, Chang Xu
Adversarial imitation learning has become a widely used imitation learning framework. The discriminator is often trained by taking expert demonstrations and policy trajectories as…
Commutative Lie Group VAE for Disentanglement Learning
Xinqi Zhu, Chang Xu, Dacheng Tao
We view disentanglement learning as discovering an underlying structure that equivariantly reflects the factorized variations shown in data. Traditionally, such a structure is fixe…
Joint Distribution across Representation Space for Out-of-Distribution Detection
JingWei Xu, Siyuan Zhu, Zenan Li +1
Deep neural networks (DNNs) have become a key part of many modern software applications. After training and validating, the DNN is deployed as an irrevocable component and applied…
LocalDrop: A Hybrid Regularization for Deep Neural Networks
Ziqing Lu, Chang Xu, Bo Du +3
In neural networks, developing regularization algorithms to settle overfitting is one of the major study areas. We propose a new approach for the regularization of neural networks…
Automatic low-bit hybrid quantization of neural networks through meta learning
Tao Wang, Junsong Wang, Chang Xu +1
Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference, especially when deploying to edge or IoT devices with limited computat…
K-Core based Temporal Graph Convolutional Network for Dynamic Graphs
Jingxin Liu, Chang Xu, Chang Yin +2
Graph representation learning is a fundamental task in various applications that strives to learn low-dimensional embeddings for nodes that can preserve graph topology information.…
Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks
Yehui Tang, Yunhe Wang, Yixing Xu +4
Deep neural networks often consist of a great number of trainable parameters for extracting powerful features from given datasets. On one hand, massive trainable parameters signifi…
On Positive-Unlabeled Classification in GAN
Tianyu Guo, Chang Xu, Jiajun Huang +4
This paper defines a positive and unlabeled classification problem for standard GANs, which then leads to a novel technique to stabilize the training of the discriminator in GANs.…
Positive-Unlabeled Compression on the Cloud
Yixing Xu, Yunhe Wang, Hanting Chen +4
Many attempts have been done to extend the great success of convolutional neural networks (CNNs) achieved on high-end GPU servers to portable devices such as smart phones. Providin…
Data-Free Learning of Student Networks
Hanting Chen, Yunhe Wang, Chang Xu +6
Learning portable neural networks is very essential for computer vision for the purpose that pre-trained heavy deep models can be well applied on edge devices such as mobile phones…
Robust Student Network Learning
Tianyu Guo, Chang Xu, Shiyi He +3
Deep neural networks bring in impressive accuracy in various applications, but the success often relies on the heavy network architecture. Taking well-trained heavy networks as tea…