Search Results for author: Bin Dai

Found 16 papers, 7 papers with code

On the Value of Infinite Gradients in Variational Autoencoder Models

no code implementations NeurIPS 2021 Bin Dai, Li Wenliang, David Wipf

A number of recent studies of continuous variational autoencoder (VAE) models have noted, either directly or indirectly, the tendency of various parameter gradients to drift towards infinity during training.

feature selection

Trajectory Prediction for Autonomous Driving with Topometric Map

1 code implementation9 May 2021 Jiaolong Xu, Liang Xiao, Dawei Zhao, Yiming Nie, Bin Dai

The experimental results show that the proposed method outperforms state-of-the-art multimodal methods and is robust to the perturbations of the topometric map.

Autonomous Driving Trajectory Prediction

Attentional Graph Neural Network for Parking-slot Detection

1 code implementation6 Apr 2021 Chen Min, Jiaolong Xu, Liang Xiao, Dawei Zhao, Yiming Nie, Bin Dai

Deep learning has recently demonstrated its promising performance for vision-based parking-slot detection.

Further Analysis of Outlier Detection with Deep Generative Models

1 code implementation NeurIPS 2020 Ziyu Wang, Bin Dai, David Wipf, Jun Zhu

The recent, counter-intuitive discovery that deep generative models (DGMs) can frequently assign a higher likelihood to outliers has implications for both outlier detection applications as well as our overall understanding of generative modeling.

Outlier Detection

Active Disturbance Rejection Control Design with Suppression of Sensor Noise Effects in Application to DC-DC Buck Power Converter

no code implementations7 Sep 2020 Krzysztof Łakomy, Rafal Madonski, Bin Dai, Jun Yang, Piotr Kicki, Maral Ansari, Shihua Li

The performance of active disturbance rejection control (ADRC) algorithms can be limited in practice by high-frequency measurement noise.

The Usual Suspects? Reassessing Blame for VAE Posterior Collapse

no code implementations ICML 2020 Bin Dai, Ziyu Wang, David Wipf

In narrow asymptotic settings Gaussian VAE models of continuous data have been shown to possess global optima aligned with ground-truth distributions.

Diagnosing and Enhancing VAE Models

4 code implementations ICLR 2019 Bin Dai, David Wipf

Although variational autoencoders (VAEs) represent a widely influential deep generative model, many aspects of the underlying energy function remain poorly understood.

Compressing Neural Networks using the Variational Information Bottelneck

1 code implementation ICML 2018 Bin Dai, Chen Zhu, Baining Guo, David Wipf

Neural networks can be compressed to reduce memory and computational requirements, or to increase accuracy by facilitating the use of a larger base architecture.

Compressing Neural Networks using the Variational Information Bottleneck

1 code implementation ICML 2018 Bin Dai, Chen Zhu, David Wipf

Neural networks can be compressed to reduce memory and computational requirements, or to increase accuracy by facilitating the use of a larger base architecture.

Understanding and Predicting The Attractiveness of Human Action Shot

no code implementations2 Nov 2017 Bin Dai, Baoyuan Wang, Gang Hua

Selecting attractive photos from a human action shot sequence is quite challenging, because of the subjective nature of the "attractiveness", which is mainly a combined factor of human pose in action and the background.

Hidden Talents of the Variational Autoencoder

1 code implementation16 Jun 2017 Bin Dai, Yu Wang, John Aston, Gang Hua, David Wipf

Variational autoencoders (VAE) represent a popular, flexible form of deep generative model that can be stochastically fit to samples from a given random process using an information-theoretic variational bound on the true underlying distribution.

Dimensionality Reduction

Multivariate Bernoulli distribution

no code implementations8 Jun 2012 Bin Dai, Shilin Ding, Grace Wahba

In this paper, we consider the multivariate Bernoulli distribution as a model to estimate the structure of graphs with binary nodes.

Variable Selection

Cannot find the paper you are looking for? You can Submit a new open access paper.