How Architecture and Training Affect TPC Representations Across Experiments

• URL: http://arxiv.org/abs/2608.21756v2
• Date: Thu, 27 Aug 2026 21:33:45 GMT
• Title: How Architecture and Training Affect TPC Representations Across Experiments
• Abstract summary: This work evaluates the reusability of representations across experiments and detector systems using probes on frozen encoders.<n>We produce 512-dimensional embeddings for four datasets from the GADGET II TPC and AT-TPC.<n>We find that this architecture-induced structure remains useful across experiments and detector systems.
• Score: 5.2143887994642215
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep-learning efforts have increasingly shifted toward foundation model approaches. In experimental physics, this allows models and learned representations to be reused beyond the experiments in which they were developed. This work evaluates the reusability of representations across experiments and detector systems using probes on frozen encoders. These probes reveal task-relevant structure before downstream adaptation, complementing fine-tuning. Together with random-weight controls, they distinguish contributions from architecture and encoder training that downstream performance alone cannot resolve. Time projection chamber (TPC) data provide a useful testbed because events from TPC systems can be represented as variable-length sparse tensors, while detector geometries, event topologies, and scientific tasks can differ substantially. We investigate whether fixed-dimensional TPC event representations can be reused across classification tasks, experiments, and detector systems. Sparse ResNet and PointNet-style encoders produce 512-dimensional embeddings for four datasets from the GADGET II TPC and AT-TPC. Randomly initialized encoders isolate the contribution from architecture before supervised training. We then train each encoder on a classification task, freeze its parameters, and train a linear or nonlinear probe for each downstream task. We find that this architecture-induced structure remains useful across experiments and detector systems. The randomly initialized PointNet-style representation is highly informative on several tasks. The two architectures organize their embedding spaces differently, but neither exhibits a large, systematic loss of utility cross-detector. These results show that architecture is a major source of task-relevant structure in TPC embeddings and should be treated explicitly when assessing representation learning and developing reusable detector models.

Related papers

• WUTDet: A 100K-Scale Ship Detection Dataset and Benchmarks with Dense Small Objects [68.44670476527155]
  WUTDet is a large-scale ship detection dataset with 100,576 images and 381,378 annotated ship instances.<n>We systematically evaluate 20 baseline models from three mainstream detection architectures, namely CNN, Transformer, and Mamba.<n>Results on Ship-GEN show that models trained on WUTDet exhibit stronger generalization under different data distributions.
  arXiv  Detail & Related papers  (2026-04-09T03:28:05Z)
• Sparse Methods for Vector Embeddings of TPC Data [6.006807882645748]
  Time Projection Chambers (TPCs) are versatile detectors that reconstruct charged-particle tracks in an ionizing medium.<n>We explore sparse convolutional networks for representation learning on TPC data.<n>We find that even an untrained sparse ResNet model provides useful embeddings of AT-TPC data.
  arXiv  Detail & Related papers  (2025-11-14T12:25:54Z)
• MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining [73.81862342673894]
  Foundation models have reshaped the landscape of Remote Sensing (RS) by enhancing various image interpretation tasks. transferring the pretrained models to downstream tasks may encounter task discrepancy due to their formulation of pretraining as image classification or object discrimination tasks. We conduct multi-task supervised pretraining on the SAMRS dataset, encompassing semantic segmentation, instance segmentation, and rotated object detection. Our models are finetuned on various RS downstream tasks, such as scene classification, horizontal and rotated object detection, semantic segmentation, and change detection.
  arXiv  Detail & Related papers  (2024-03-20T09:17:22Z)
• SimPLR: A Simple and Plain Transformer for Efficient Object Detection and Segmentation [49.65221743520028]
  We show that shifting the multiscale inductive bias into the attention mechanism can work well, resulting in a plain detector SimPLR'<n>We find through our experiments that SimPLR with scale-aware attention is plain and simple architecture, yet competitive with multi-scale vision transformer alternatives.
  arXiv  Detail & Related papers  (2023-10-09T17:59:26Z)
• Unpaired Image Translation to Mitigate Domain Shift in Liquid Argon Time Projection Chamber Detector Responses [5.799883835053843]
  The " domain shift problem" is prevalent in many scientific domains where algorithms are trained on simulated data but applied to real-world datasets. This work explores the feasibility of using an alternative way to solve the domain shift problem that is not specific to any downstream algorithm. The proposed approach relies on modern Unpaired Image-to-Image translation techniques, designed to find translations between different image domains in a fully unsupervised fashion.
  arXiv  Detail & Related papers  (2023-04-25T14:29:54Z)
• Strong Baselines for Parameter Efficient Few-Shot Fine-tuning [50.83426196335385]
  Few-shot classification (FSC) entails learning novel classes given only a few examples per class after a pre-training (or meta-training) phase. Recent works have shown that simply fine-tuning a pre-trained Vision Transformer (ViT) on new test classes is a strong approach for FSC. Fine-tuning ViTs, however, is expensive in time, compute and storage. This has motivated the design of parameter efficient fine-tuning (PEFT) methods which fine-tune only a fraction of the Transformer's parameters.
  arXiv  Detail & Related papers  (2023-04-04T16:14:39Z)
• CvT-ASSD: Convolutional vision-Transformer Based Attentive Single Shot MultiBox Detector [15.656374849760734]
  We present a novel object detection architecture, named Convolutional vision Transformer Based Attentive Single Shot MultiBox Detector (CvT-ASSD) Our model CvT-ASSD can leads to good system efficiency and performance while being pretrained on large-scale detection datasets such as PASCAL VOC and MS COCO.
  arXiv  Detail & Related papers  (2021-10-24T06:45:33Z)
• The Nonlinearity Coefficient -- A Practical Guide to Neural Architecture Design [3.04585143845864]
  We develop methods that can predict, without any training, whether an architecture will achieve a relatively high test or training error on a task after training. We then go on to explain the error in terms of the architecture definition itself and develop tools for modifying the architecture. Our first major contribution is to show that the 'degree of nonlinearity' of a neural architecture is a key causal driver behind its performance.
  arXiv  Detail & Related papers  (2021-05-25T20:47:43Z)
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
  We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
  arXiv  Detail & Related papers  (2021-03-17T08:28:30Z)
• Unsupervised Monocular Depth Learning with Integrated Intrinsics and Spatio-Temporal Constraints [61.46323213702369]
  This work presents an unsupervised learning framework that is able to predict at-scale depth maps and egomotion. Our results demonstrate strong performance when compared to the current state-of-the-art on multiple sequences of the KITTI driving dataset.
  arXiv  Detail & Related papers  (2020-11-02T22:26:58Z)
• MultiCheXNet: A Multi-Task Learning Deep Network For Pneumonia-like Diseases Diagnosis From X-ray Scans [1.0621485365427565]
  MultiCheXNet is able to take advantage of different X-rays data sets of Pneumonia-like diseases in one neural architecture. The common encoder in our architecture can capture useful common features present in the different tasks. The specialized decoders heads can then capture the task-specific features.
  arXiv  Detail & Related papers  (2020-08-05T07:45:24Z)
• The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures [179.66117325866585]
  We investigate a design space that is usually overlooked, i.e. adjusting the channel configurations of predefined networks. We find that this adjustment can be achieved by shrinking widened baseline networks and leads to superior performance. Experiments are conducted on various networks and datasets for image classification, visual tracking and image restoration.
  arXiv  Detail & Related papers  (2020-06-29T17:59:26Z)

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.