5 citations · 5 across the 14 of their papers we have counts for
15 papers
Visual Prompting Meets Feature Reconstruction-Based Anomaly Detection with Dual-Teacher Supervision
Mateo Diaz-Bone, Daniel Caraballo, Florian Scheidegger +11
Recent Anomaly Detection methods achieve perfect detection and segmentation scores on well-established datasets, such as MVTec. However, many of these methods face challenges when…
Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models
Nicola Farronato, Niccolo Avogaro, Thomas Frick +6
Automated structural health monitoring is essential to prevent catastrophic infrastructure failures. Precise, pixel-level defect segmentation is needed to accurately assess structu…
Towards a Foundation Model for Partial Differential Equations Across Physics Domains
Eduardo Soares, Emilio Vital Brazil, Victor Shirasuna +2
We present PDE-FM, a modular foundation model for physics-informed machine learning that unifies spatial, spectral, and temporal reasoning across heterogeneous partial differential…
Enhancing Semantic Segmentation with Continual Self-Supervised Pre-training
Brown Ebouky, Ajad Chhatkuli, Cristiano Malossi +3
Self-supervised learning (SSL) has emerged as a central paradigm for training foundation models by leveraging large-scale unlabeled datasets, often producing representations with s…
Q-SAM2: Accurate Quantization for Segment Anything Model 2
Nicola Farronato, Florian Scheidegger, Mattia Rigotti +3
The Segment Anything Model 2 (SAM2) is a powerful foundation model for promptable segmentation. However, its high computational and memory costs are a major barrier to deployment o…
VP Lab: a PEFT-Enabled Visual Prompting Laboratory for Semantic Segmentation
Niccolo Avogaro, Thomas Frick, Yagmur G. Cinar +12
Large-scale pretrained vision backbones have transformed computer vision by providing powerful feature extractors that enable various downstream tasks, including training-free appr…
Show or Tell? Effectively prompting Vision-Language Models for semantic segmentation
Niccolo Avogaro, Thomas Frick, Mattia Rigotti +5
Large Vision-Language Models (VLMs) are increasingly being regarded as foundation models that can be instructed to solve diverse tasks by prompting, without task-specific training.…
Outline-Guided Object Inpainting with Diffusion Models
Markus Pobitzer, Filip Janicki, Mattia Rigotti +1
Instance segmentation datasets play a crucial role in training accurate and robust computer vision models. However, obtaining accurate mask annotations to produce high-quality segm…
Active Learning for Imbalanced Civil Infrastructure Data
Thomas Frick, Diego Antognini, Mattia Rigotti +3
Aging civil infrastructures are closely monitored by engineers for damage and critical defects. As the manual inspection of such large structures is costly and time-consuming, we a…
Model-Assisted Labeling via Explainability for Visual Inspection of Civil Infrastructures
Klara Janouskova, Mattia Rigotti, Ioana Giurgiu +1
Labeling images for visual segmentation is a time-consuming task which can be costly, particularly in application domains where labels have to be provided by specialized expert ann…
Enabling Reproducibility and Meta-learning Through a Lifelong Database of Experiments (LDE)
Jason Tsay, Andrea Bartezzaghi, Aleke Nolte +1
Artificial Intelligence (AI) development is inherently iterative and experimental. Over the course of normal development, especially with the advent of automated AI, hundreds or th…
Generating Efficient DNN-Ensembles with Evolutionary Computation
Marc Ortiz, Florian Scheidegger, Marc Casas +2
In this work, we leverage ensemble learning as a tool for the creation of faster, smaller, and more accurate deep learning models. We demonstrate that we can jointly optimize for a…
Reducing Data Motion to Accelerate the Training of Deep Neural Networks
Sicong Zhuang, Cristiano Malossi, Marc Casas
This paper reduces the cost of DNNs training by decreasing the amount of data movement across heterogeneous architectures composed of several GPUs and multicore CPU devices. In par…
Efficient Image Dataset Classification Difficulty Estimation for Predicting Deep-Learning Accuracy
Florian Scheidegger, Roxana Istrate, Giovanni Mariani +3
In the deep-learning community new algorithms are published at an incredible pace. Therefore, solving an image classification problem for new datasets becomes a challenging task, a…
Simulation of left ventricle fluid dynamics with mitral regurgitation from magnetic resonance images with fictitious elastic structure regularization
Toni Lassila, Cristiano Malossi, Marco Stevanella +3
Computer modeling can provide quantitative insight into cardiac fluid dynamics phenomena that are not evident from standard imaging tools. We propose a new approach to modeling lef…