1 citations · 1 across the 11 of their papers we have counts for
11 papers
AgriField-40K: Adapting Vision Models to Agriculture With Efficient Continual Pretraining
Vasileios Tzouras, Paraskevas Pegios, Lazaros Nalpantidis
Field-based agricultural computer vision is important for precision agriculture, yet it largely depends on expensive annotations and costly adaptation of large pretrained models. W…
Need for Speed: Zero-Shot Depth Completion with Single-Step Diffusion
Jakub Gregorek, Paraskevas Pegios, Nando Metzger +3
We introduce Marigold-SSD, a single-step, late-fusion depth completion framework that leverages strong diffusion priors while eliminating the costly test-time optimization typicall…
Weight Space Correlation Analysis: Quantifying Feature Utilization in Deep Learning Models
Chun Kit Wong, Paraskevas Pegios, Nina Weng +4
Deep learning models in medical imaging are susceptible to shortcut learning, relying on confounding metadata (e.g., scanner model) that is often encoded in image embeddings. The c…
Causally Steered Diffusion for Automated Video Counterfactual Generation
Nikos Spyrou, Athanasios Vlontzos, Paraskevas Pegios +5
Adapting text-to-image (T2I) latent diffusion models (LDMs) to video editing has shown strong visual fidelity and controllability, but challenges remain in maintaining causal relat…
Graph Counterfactual Explainable AI via Latent Space Traversal
Andreas Abildtrup Hansen, Paraskevas Pegios, Anna Calissano +1
Explaining the predictions of a deep neural network is a nontrivial task, yet high-quality explanations for predictions are often a prerequisite for practitioners to trust these mo…
Counterfactual Explanations via Riemannian Latent Space Traversal
Paraskevas Pegios, Aasa Feragen, Andreas Abildtrup Hansen +1
The adoption of increasingly complex deep models has fueled an urgent need for insight into how these models make predictions. Counterfactual explanations form a powerful tool for…
Unsupervised Detection of Fetal Brain Anomalies using Denoising Diffusion Models
Markus Ditlev Sjøgren Olsen, Jakob Ambsdorf, Manxi Lin +7
Congenital malformations of the brain are among the most common fetal abnormalities that impact fetal development. Previous anomaly detection methods on ultrasound images are based…
Diffusion-based Iterative Counterfactual Explanations for Fetal Ultrasound Image Quality Assessment
Paraskevas Pegios, Manxi Lin, Nina Weng +6
Obstetric ultrasound image quality is crucial for accurate diagnosis and monitoring of fetal health. However, acquiring high-quality standard planes is difficult, influenced by the…
Learning semantic image quality for fetal ultrasound from noisy ranking annotation
Manxi Lin, Jakob Ambsdorf, Emilie Pi Fogtmann Sejer +9
We introduce the notion of semantic image quality for applications where image quality relies on semantic requirements. Working in fetal ultrasound, where ranking is challenging an…
Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation
Nina Weng, Paraskevas Pegios, Eike Petersen +2
Shortcut learning is when a model -- e.g. a cardiac disease classifier -- exploits correlations between the target label and a spurious shortcut feature, e.g. a pacemaker, to predi…
Style Decomposition for Improved Neural Style Transfer
Paraskevas Pegios, Nikolaos Passalis, Anastasios Tefas
Universal Neural Style Transfer (NST) methods are capable of performing style transfer of arbitrary styles in a style-agnostic manner via feature transforms in (almost) real-time.…