13 citations · 28 across the 14 of their papers we have counts for
14 papers
Prescriptive SVD-Inspired Attention via Spectral Energy Retention
Vasileios Arampatzakis, Vasileios Sevetlidis, George Pavlidis
Self-attention is central to modern Transformer architectures, but its dense dot-product formulation makes it difficult to identify which internal directions are structurally impor…
Loss-Shift Transfer via Bayes Quotients
Vasileios Sevetlidis
Transfer learning is usually studied as a consequence of distribution shift. This paper identifies an orthogonal failure mode in which the data distribution is fixed and the loss c…
Bayes-Sufficient Representations in Supervised Learning
Vasileios Sevetlidis
Representation learning is often described as preserving the information in an input that is relevant for prediction. This work asks what relevance means for a fixed supervised dec…
A Fiber Criterion for Representation Identifiability in Supervised Learning
Vasileios Sevetlidis
Supervised learning evaluates predictors through their input-output behavior. When a predictor is implemented as a composition , supervised evidence constrains the comp…
Towards complete digital twins in cultural heritage with ART3mis 3D artifacts annotator
Dimitrios Karamatskos, Vasileios Arampatzakis, Vasileios Sevetlidis +5
Archaeologists, as well as specialists and practitioners in cultural heritage, require applications with additional functions, such as the annotation and attachment of metadata to…
ART3mis: Ray-Based Textual Annotation on 3D Cultural Objects
Vasileios Arampatzakis, Vasileios Sevetlidis, Fotis Arnaoutoglou +7
Beyond simplistic 3D visualisations, archaeologists, as well as cultural heritage experts and practitioners, need applications with advanced functionalities. Such as the annotation…
Gauge-invariant representation holonomy
Vasileios Sevetlidis, George Pavlidis
Deep networks learn internal representations whose geometry--how features bend, rotate, and evolve--affects both generalization and robustness. Existing similarity measures such as…
Training Memory in Deep Neural Networks: Mechanisms, Evidence, and Measurement Gaps
Vasileios Sevetlidis, George Pavlidis
Modern deep-learning training is not memoryless. Updates depend on optimizer moments and averaging, data-order policies (random reshuffling vs with-replacement, staged augmentation…
Process-Tensor Tomography of SGD: Measuring Non-Markovian Memory via Back-Flow of Distinguishability
Vasileios Sevetlidis, George Pavlidis
This work proposes neural training as a \emph{process tensor}: a multi-time map that takes a sequence of controllable instruments (batch choices, augmentations, optimizer micro-ste…
Angular Regularization for Positive-Unlabeled Learning on the Hypersphere
Vasileios Sevetlidis, George Pavlidis, Antonios Gasteratos
Positive-Unlabeled (PU) learning addresses classification problems where only a subset of positive examples is labeled and the remaining data is unlabeled, making explicit negative…
A Unified Framework for Cultural Heritage Data Historicity and Migration: The ARGUS Approach
Lingxiao Kong, Apostolos Sarris, Miltiadis Polidorou +6
Cultural heritage preservation faces significant challenges in managing diverse, multi-source, and multi-scale data for effective monitoring and conservation. This paper documents…
Deep learning based black spot identification on Greek road networks
Ioannis Karamanlis, Alexandros Kokkalis, Vassilios Profillidis +4
Black spot identification, a spatiotemporal phenomenon, involves analyzing the geographical location and time-based occurrence of road accidents. Typically, this analysis examines…
Defect detection using weakly supervised learning
Vasileios Sevetlidis, George Pavlidis, Vasiliki Balaska +3
In many real-world scenarios, obtaining large amounts of labeled data can be a daunting task. Weakly supervised learning techniques have gained significant attention in recent year…
Dens-PU: PU Learning with Density-Based Positive Labeled Augmentation
Vasileios Sevetlidis, George Pavlidis, Spyridon Mouroutsos +1
This study proposes a novel approach for solving the PU learning problem based on an anomaly-detection strategy. Latent encodings extracted from positive-labeled data are linearly…