Novel tracking approach based on fully-unsupervised disentanglement of the geometrical factors of variation

Abstract

Efficient tracking algorithms are a crucial part of particle tracking detectors. While a lot of work has been done in designing a plethora of algorithms, these usually require tedious tuning for each use case. (Weakly) supervised Machine Learning-based approaches can leverage the actual raw data for maximal performance. Yet in realistic scenarios, sufficient high-quality labeled data is not available. While training might be performed on simulated data, the reproduction of realistic signal and noise in the detector requires substantial effort, compromising this approach. Here we propose a novel, fully unsupervised, approach to track reconstruction. The introduced model for learning to disentangle the factors of variation in a geometrically meaningful way employs geometrical space invariances. We train it through constraints on the equivariance between the image space and the latent representation in a Deep Convolutional Autoencoder. Using experimental results on synthetic data we show that a combination of different space transformations is required for meaningful disentanglement of factors of variation. We also demonstrate the performance of our model on real data from tracking detectors.

arXiv commentAccepted for publication in JINST

References in corpus (9)

• Observation of Tau Neutrino Interactions
• Discovery of tau neutrino appearance in the CNGS neutrino beam with the OPERA experiment
• Convolutional Neural Networks Applied to Neutrino Events in a Liquid Argon Time Projection Chamber
• A Deep Neural Network for Pixel-Level Electromagnetic Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
• Hyper-track selector nuclear emulsion readout system aimed at scanning an area of one thousand square meters
• DsTau: Study of tau neutrino production with 400 GeV protons from the CERN-SPS
• First Measurement of ${\nu }_{\mu }$ Charged-Current ${\pi }^0$ Production on Argon with a LArTPC
• Fast 4$\pi$ track reconstruction in nuclear emulsion detectors based on GPU technology
• Nuclear emulsions for the detection of micrometric-scale fringe patterns: an application to positron interferometry