IDLat: An Importance-Driven Latent Generation Method for Scientific Data

• URL: http://arxiv.org/abs/2208.03345v1
• Date: Fri, 5 Aug 2022 18:23:22 GMT
• Title: IDLat: An Importance-Driven Latent Generation Method for Scientific Data
• Authors: Jingyi Shen, Haoyu Li, Jiayi Xu, Ayan Biswas, and Han-Wei Shen
• Abstract summary: We present a novel importance-driven latent representation to facilitate domain-interest-guided scientific data visualization and analysis. We utilize spatial importance maps to represent various scientific interests and take them as the input to a feature transformation network to guide latent generation.
• Score: 12.93181915755184
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning based latent representations have been widely used for numerous scientific visualization applications such as isosurface similarity analysis, volume rendering, flow field synthesis, and data reduction, just to name a few. However, existing latent representations are mostly generated from raw data in an unsupervised manner, which makes it difficult to incorporate domain interest to control the size of the latent representations and the quality of the reconstructed data. In this paper, we present a novel importance-driven latent representation to facilitate domain-interest-guided scientific data visualization and analysis. We utilize spatial importance maps to represent various scientific interests and take them as the input to a feature transformation network to guide latent generation. We further reduced the latent size by a lossless entropy encoding algorithm trained together with the autoencoder, improving the storage and memory efficiency. We qualitatively and quantitatively evaluate the effectiveness and efficiency of latent representations generated by our method with data from multiple scientific visualization applications.

Related papers

• Label-Efficient Skeleton-based Recognition with Stable-Invertible Graph Convolutional Networks [14.061680807550722]
  This paper devises a novel, label-efficient method for skeleton-based action recognition using graph convolutional networks (GCNs)<n>The contribution of the proposed method resides in learning a novel acquisition function -- scoring the most informative subsets for labeling.<n>We also extend this approach by learning the most informative subsets using an invertible GCN which allows mapping data from ambient to latent spaces.
  arXiv  Detail & Related papers  (2025-11-21T16:06:53Z)
• Compressive Modeling and Visualization of Multivariate Scientific Data using Implicit Neural Representation [5.742682177744733]
  We develop compressed neural representations for datasets containing tens to hundreds of variables.<n>Our approach utilizes a single network to learn rendering representations for all data variables simultaneously.<n>We demonstrate superior performance in terms of reconstructed data quality, visualization quality, preservation of dependency information among variables, and storage efficiency.
  arXiv  Detail & Related papers  (2025-10-17T11:09:55Z)
• Simultaneous Dimensionality Reduction for Extracting Useful Representations of Large Empirical Multimodal Datasets [0.0]
  We focus on the sciences of dimensionality reduction as a means to obtain low-dimensional descriptions from high-dimensional data. We address the challenges posed by real-world data that defy conventional assumptions, such as complex interactions within systems or high-dimensional dynamical systems.
  arXiv  Detail & Related papers  (2024-10-23T21:27:40Z)
• A Simple Background Augmentation Method for Object Detection with Diffusion Model [53.32935683257045]
  In computer vision, it is well-known that a lack of data diversity will impair model performance. We propose a simple yet effective data augmentation approach by leveraging advancements in generative models. Background augmentation, in particular, significantly improves the models' robustness and generalization capabilities.
  arXiv  Detail & Related papers  (2024-08-01T07:40:00Z)
• Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems [80.62854148838359]
  Eye image segmentation is a critical step in eye tracking that has great influence over the final gaze estimate. We use dimensionality-reduction techniques to measure the overlap between the target eye images and synthetic training data. Our methods result in robust, improved performance when tackling the discrepancy between simulation and real-world data samples.
  arXiv  Detail & Related papers  (2024-03-23T22:32:06Z)
• Discrete transforms of quantized persistence diagrams [0.5249805590164902]
  We introduce Qupid, a novel and simple method for vectorizing persistence diagrams. Key features are the choice of log-scaled grids that emphasize information contained near the diagonal in persistence diagrams. We conduct an in-depth experimental analysis of Qupid, showing that the simplicity of our method results in very low computational costs.
  arXiv  Detail & Related papers  (2023-12-28T16:11:11Z)
• MDFL: Multi-domain Diffusion-driven Feature Learning [19.298491870280213]
  We present a multi-domain diffusion-driven feature learning network (MDFL) MDFL redefines the effective information domain that the model really focuses on. We demonstrate that MDFL significantly improves the feature extraction performance of high-dimensional data.
  arXiv  Detail & Related papers  (2023-11-16T02:55:21Z)
• Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances [76.34037366117234]
  We introduce a new dataset called Robot Control Gestures (RoCoG-v2) The dataset is composed of both real and synthetic videos from seven gesture classes. We present results using state-of-the-art action recognition and domain adaptation algorithms.
  arXiv  Detail & Related papers  (2023-03-17T23:23:55Z)
• TMHOI: Translational Model for Human-Object Interaction Detection [18.804647133922195]
  We propose an innovative graph-based approach to detect human-object interactions (HOIs) Our method effectively captures the sentiment representation of HOIs by integrating both spatial and semantic knowledge. Our approach outperformed existing state-of-the-art graph-based methods by a significant margin.
  arXiv  Detail & Related papers  (2023-03-07T21:52:10Z)
• Information-Theoretic Odometry Learning [83.36195426897768]
  We propose a unified information theoretic framework for learning-motivated methods aimed at odometry estimation. The proposed framework provides an elegant tool for performance evaluation and understanding in information-theoretic language.
  arXiv  Detail & Related papers  (2022-03-11T02:37:35Z)
• Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders [63.46738617561255]
  We consider the problem of sparsifying the discrete latent space of a trained conditional variational autoencoder. We use evidential theory to identify the latent classes that receive direct evidence from a particular input condition and filter out those that do not. Experiments on diverse tasks, such as image generation and human behavior prediction, demonstrate the effectiveness of our proposed technique.
  arXiv  Detail & Related papers  (2020-10-19T01:27:21Z)
• Graph Representation Learning via Graphical Mutual Information Maximization [86.32278001019854]
  We propose a novel concept, Graphical Mutual Information (GMI), to measure the correlation between input graphs and high-level hidden representations. We develop an unsupervised learning model trained by maximizing GMI between the input and output of a graph neural encoder.
  arXiv  Detail & Related papers  (2020-02-04T08:33:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.