10–14 Nov 2025
The University of Tokyo
Asia/Tokyo timezone

Semi-Supervised Transfer Learning with Convolutional Autoencoders for Hybrid Pixel Detectors

10 Nov 2025, 15:05
25m
Talk Session

Speaker

Mr Tomáš Čelko (Charles University)

Description

Hybrid pixel detectors such as Timepix3 and Timepix4 enable pixel-level resolution of individual particle interactions, where each event manifests as a cluster or track spanning multiple pixels. Analyzing these clusters allows for the estimation of key particle parameters, including type, initial energy, and angle of incidence. However, such ground-truth parameters are typically unavailable during data acquisition, necessitating the use of simulations, which are often computationally intensive and may fail to capture detector imperfections and noise. A central challenge is thus leveraging unlabeled experimental data alongside simulations for training. To address this, we propose a semi-supervised approach that pretrains convolutional autoencoders—specifically U-Net architectures with EfficientNet backbones—on unlabeled measured data. These models are subsequently fine-tuned on labeled simulations for classification and regression tasks. To interpret the learned latent representations, we employ t-distributed Stochastic Neighbor Embedding (t-SNE) and Uniform Manifold Approximation and Projection (UMAP). Finally, we show that self-supervised pertaining improves the classification of simulated protons and electrons and enhances incidence angle regression within the Space Application of Timepix Radiation Monitor (SATRAM) context.

Author

Mr Tomáš Čelko (Charles University)

Co-authors

Presentation materials