Vision Calorimeter: Migrating Visual Object Detector to High-energy Particle Images

2024-08-20

AI Summary

In high-energy physics, electromagnetic calorimeters (EMCs) suffer from limited accuracy in estimating the incident position and momentum of antineutrons ($ar{n}$). To address this, we propose the first end-to-end, data-driven framework for particle image analysis inspired by computer vision object detection, grounded in a heat conduction mechanism. Our method introduces a novel Heat Conduction Operator (HCO) that jointly incorporates radial prior knowledge and global attention, and employs Discrete Cosine Transform (DCT) to align feature distributions in the frequency domain, enabling effective cross-modal transfer. The HCO is integrated into both the backbone and detection head of an enhanced detector architecture, while frequency-domain features are explicitly modeled. Experiments demonstrate a 46.16% reduction in incident position prediction error (from 17.31° to 9.32°) and achieve the first reported incident momentum regression error of 21.48%, establishing the inaugural benchmark for this task.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Multi-modal Vision
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

In high-energy physics, accurately estimating the kinematic parameters (position and momentum) of anti-neutrons ($ar{n}$) is essential for exploring the fundamental governing principles. However, this process is particularly challenging when using an electromagnetic calorimeter (EMC) as the energy detector, due to their limited accuracy and efficiency in interacting with $ar{n}$. To address this issue, we propose Vision Calorimeter (ViC), a data-driven framework which migrates visual object detection techniques to high-energy particle images. To accommodate the unique characteristics of particle images, we introduce the heat-conduction operator (HCO) into both the backbone and the head of the conventional object detector and conduct significant structural improvements. HCO enjoys the advantage of both radial prior and global attention, as it is inspired by physical heat conduction which naturally aligns with the pattern of particle incidence. Implemented via the Discrete Cosine Transform (DCT), HCO extracts frequency-domain features, bridging the distribution gap between the particle images and the natural images on which visual object detectors are pre-trained. Experimental results demonstrate that ViC significantly outperforms traditional approaches, reducing the incident position prediction error by 46.16% (from 17.31$^{circ}$ to 9.32$^{circ}$) and providing the first baseline result with an incident momentum regression error of 21.48%. This study underscores ViC's great potential as a general-purpose particle parameter estimator in high-energy physics. Code is available at https://github.com/yuhongtian17/ViC.

Problem

• Enhance anti-neutron kinematic parameter estimation.
• Migrate visual detection to particle images.
• Introduce heat-conduction operator for accuracy.

Innovation

• Migrates visual object detection techniques
• Introduces heat-conduction operator (HCO)
• Extracts frequency-domain features via DCT