paper-with-me

Papers

Fast 2D Bicephalous Convolutional Autoencoder for Compressing 3D Time Projection Chamber Data

2023-10-23 · Yi Huang, Yihui Ren, Shinjae Yoo, Jin Huang

High-energy large-scale particle colliders produce data at high speed in the order of 1 terabytes per second in nuclear physics and petabytes per second in high-energy physics. Developing real-time data compression algorithms to reduce such data at high throughput to fit permanent storage has drawn increasing attention. Specifically, at the newly constructed sPHENIX experiment at the Relativistic Heavy Ion Collider (RHIC), a time projection chamber is used as the main tracking detector, which records particle trajectories in a volume of a three-dimensional (3D) cylinder. The resulting data are usually very sparse with occupancy around 10.8%. Such sparsity presents a challenge to conventional learning-free lossy compression algorithms, such as SZ, ZFP, and MGARD. The 3D convolutional neural network (CNN)-based approach, Bicephalous Convolutional Autoencoder (BCAE), outperforms traditional methods both in compression rate and reconstruction accuracy. BCAE can also utilize the computation power of graphical processing units suitable for deployment in a modern heterogeneous high-performance computing environment. This work introduces two BCAE variants: BCAE++ and BCAE-2D. BCAE++ achieves a 15% better compression ratio and a 77% better reconstruction accuracy measured in mean absolute error compared with BCAE. BCAE-2D treats the radial direction as the channel dimension of an image, resulting in a 3x speedup in compression throughput. In addition, we demonstrate an unbalanced autoencoder with a larger decoder can improve reconstruction accuracy without significantly sacrificing throughput. Lastly, we observe both the BCAE++ and BCAE-2D can benefit more from using half-precision mode in throughput (76-79% increase) without loss in reconstruction accuracy. The source code and links to data and pretrained models can be found at https://github.com/BNL-DAQ-LDRD/NeuralCompression_v2.

📄 PDF Abstract BibTeX arXiv:2310.15026

Code (1)

bnl-daq-ldrd/neuralcompression_v2 공식 구현 pytorch

Tasks

Data Compression

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Efficient Data Compression for 3D Sparse TPC via Bicephalous Convolutional Autoencoder

2021-11-09 · Yi Huang, Yihui Ren, Shinjae Yoo, Jin Huang

Real-time data collection and analysis in large experimental facilities present a great challenge across multiple domains, including high energy physics, nuclear physics, and cosmology. To address this, machine learning …

Data CompressionDecoder

Lat-Net: Compressing Lattice Boltzmann Flow Simulations using Deep Neural Networks

2017-05-25 · Oliver Hennigh

Computational Fluid Dynamics (CFD) is a hugely important subject with applications in almost every engineering field, however, fluid simulations are extremely computationally and memory demanding. Towards this end, we pr…

Efficient Neural Network

Cancelable Biometric Template Generation using Convolutional Autoencoder

2021-03-26 · Computer Vision and Image Processing 2021 3 · Gourav Siddhad, Pritee Khanna, Aparajita Ojha

Convolutional autoencoders are a great tool for extracting features from images and compressing them to a lower dimension called latent space. A latent space vector is generated from the input images by extracting the re…

Adversarial Attacks on Variational Autoencoders

2018-06-12 · George Gondim-Ribeiro, Pedro Tabacof, Eduardo Valle

Adversarial attacks are malicious inputs that derail machine-learning models. We propose a scheme to attack autoencoders, as well as a quantitative evaluation framework that correlates well with the qualitative assessmen…

BIG-bench Machine Learning

Compression Method for Solar Polarization Spectra Collected from Hinode SOT/SP Observations

2024-11-14 · Jargalmaa Batmunkh, Yusuke Iida, Takayoshi Oba, Haruhisa Iijima

The complex structure and extensive details of solar spectral data, combined with a recent surge in volume, present significant processing challenges. To address this, we propose a deep learning-based compression techniq…