no code implementations • 21 Feb 2024 • Haoyu Li, Han-Wei Shen
In this paper, we present an improved technique for range analysis by revisiting the arithmetic rules and analyzing the probability distribution of the network output within a spatial region.
no code implementations • 8 Aug 2023 • Jingyi Shen, Han-Wei Shen
The efficient sampling in the Gaussian latent space allows our model to perform uncertainty quantification for the super-resolved results.
1 code implementation • 16 Jul 2023 • Skylar Wolfgang Wurster, Hanqi Guo, Tom Peterka, Han-Wei Shen
Our approach takes a vector field as input and trains an implicit neural representation to learn a stream function for that vector field.
1 code implementation • 16 Jul 2023 • Skylar Wolfgang Wurster, Tianyu Xiong, Han-Wei Shen, Hanqi Guo, Tom Peterka
We address this shortcoming with an adaptively placed multi-grid SRN (APMGSRN) and propose a domain decomposition training and inference technique for accelerated parallel training on multi-GPU systems.
no code implementations • 7 Jun 2023 • Yamei Tu, Rui Qiu, Han-Wei Shen
To extract knowledge from unstructured text, we develop a Knowledge Extraction Module that includes a semi-supervised pipeline for entity extraction and entity normalization.
no code implementations • 31 May 2023 • Jiayi Xu, Han-Wei Shen
The resulting rectangular layout has better aspect ratio quality on synthetic data compared with the existing method for the rectangular partitioning of 2D points.
1 code implementation • 15 Sep 2022 • Xiaoqi Wang, Han-Wei Shen
In this paper, we propose a model-agnostic model-level explanation method for different GNNs that follow the message passing scheme, GNNInterpreter, to explain the high-level decision-making process of the GNN model.
no code implementations • 5 Aug 2022 • Jingyi Shen, Haoyu Li, Jiayi Xu, Ayan Biswas, Han-Wei Shen
We qualitatively and quantitatively evaluate the effectiveness and efficiency of latent representations generated by our method with data from multiple scientific visualization applications.
1 code implementation • 25 Jul 2022 • Neng Shi, Jiayi Xu, Haoyu Li, Hanqi Guo, Jonathan Woodring, Han-Wei Shen
In the model inference stage, we predict the latent representations at previously selected viewpoints and decode the latent representations to data space.
1 code implementation • 23 Jun 2022 • Hong-You Chen, Cheng-Hao Tu, Ziwei Li, Han-Wei Shen, Wei-Lun Chao
To make our findings applicable to situations where pre-trained models are not directly available, we explore pre-training with synthetic data or even with clients' data in a decentralized manner, and found that they can already improve FL notably.
no code implementations • 13 Jun 2022 • Xiaoqi Wang, Kevin Yen, Yifan Hu, Han-Wei Shen
There are a few existing methods that have attempted to develop a flexible solution for optimizing different aesthetic aspects measured by different aesthetic criteria.
1 code implementation • 18 Feb 2022 • Neng Shi, Jiayi Xu, Skylar W. Wurster, Hanqi Guo, Jonathan Woodring, Luke P. Van Roekel, Han-Wei Shen
Our approach improves the efficiency of parameter space exploration with a surrogate model that predicts the simulation outputs accurately and efficiently.
no code implementations • 13 Sep 2021 • Jiayi Xu, Hanqi Guo, Han-Wei Shen, Mukund Raj, Skylar W. Wurster, Tom Peterka
Second, we propose a workload estimation model, helping RL agents estimate the workload distribution of processes in future computations.
no code implementations • 27 Jun 2021 • Xiaoqi Wang, Kevin Yen, Yifan Hu, Han-Wei Shen
In this paper, we propose a Convolutional Graph Neural Network based deep learning framework, DeepGD, which can draw arbitrary graphs once trained.
no code implementations • 30 May 2021 • Skylar W. Wurster, Hanqi Guo, Han-Wei Shen, Thomas Peterka, Jiayi Xu
We present a novel technique for hierarchical super resolution (SR) with neural networks (NNs), which upscales volumetric data represented with an octree data structure to a high-resolution uniform grid with minimal seam artifacts on octree node boundaries.
1 code implementation • 27 May 2021 • Haoyu Li, Han-Wei Shen
Feature related particle data analysis plays an important role in many scientific applications such as fluid simulations, cosmology simulations and molecular dynamics.
no code implementations • 20 May 2021 • Meng Ling, Jian Chen, Torsten Möller, Petra Isenberg, Tobias Isenberg, Michael Sedlmair, Robert S. Laramee, Han-Wei Shen, Jian Wu, C. Lee Giles
We present document domain randomization (DDR), the first successful transfer of convolutional neural networks (CNNs) trained only on graphically rendered pseudo-paper pages to real-world document segmentation.
no code implementations • 22 Dec 2020 • Jian Chen, Meng Ling, Rui Li, Petra Isenberg, Tobias Isenberg, Michael Sedlmair, Torsten Möller, Robert S. Laramee, Han-Wei Shen, Katharina Wünsche, Qiru Wang
We present the VIS30K dataset, a collection of 29, 689 images that represents 30 years of figures and tables from each track of the IEEE Visualization conference series (Vis, SciVis, InfoVis, VAST).
no code implementations • 8 Sep 2020 • Guan Li, Junpeng Wang, Han-Wei Shen, Kaixin Chen, Guihua Shan, Zhonghua Lu
It considers the importance of convolutional filters through both instability and sensitivity, and allows users to interactively create pruning plans according to a desired goal on model size or accuracy.
no code implementations • 2 May 2020 • Jingyi Shen, Han-Wei Shen
Despite the great success of Convolutional Neural Networks (CNNs) in Computer Vision and Natural Language Processing, the working mechanism behind CNNs is still under extensive discussions and research.
no code implementations • 1 Aug 2019 • Wenbin He, Junpeng Wang, Hanqi Guo, Ko-Chih Wang, Han-Wei Shen, Mukund Raj, Youssef S. G. Nashed, Tom Peterka
We propose InSituNet, a deep learning based surrogate model to support parameter space exploration for ensemble simulations that are visualized in situ.
no code implementations • 19 Apr 2019 • Subhashis Hazarika, Haoyu Li, Ko-Chih Wang, Han-Wei Shen, Ching-Shan Chou
We utilize the trained network to perform interactive parameter sensitivity analysis of the original simulation at multiple levels-of-detail as well as recommend optimal parameter configurations using the activation maximization framework of neural networks.