Publications related to Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors

Related publications (19)

Learning Algorithms in the Limit

Nicolas Henri Bernard Flammarion, Hristo Georgiev Papazov

This paper studies the problem of learning computable functions in the limit by extending Gold's inductive inference framework to incorporate computational observations and restricted input sources. Complimentary to the traditional Input-Output Observation ...

2025

Temporally-Consistent Surface Reconstruction Using Metrically-Consistent Atlases

Pascal Fua, Mathieu Salzmann, Shaifali Parashar, Jan Bednarík

We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds. It yields dense and semantically meaningful correspondences between frames. We represent the reconstructed su ...

2025

Learning Power Flow Models and Constraints from Time-Synchronised Measurements: A Review

Mario Paolone, Rahul Kumar Gupta

Key operational and protection functions of power systems (e.g., optimal power flow scheduling and control, state estimation, protection, and fault location) rely on the availability of models to represent the system's behavior under different operating co ...

Institute of Electrical and Electronics Engineers (IEEE)2025

An Analysis of Model Robustness across Concurrent Distribution Shifts

Myeongho Jeon, Shuqing Teresa Yeo

Machine learning models, meticulously optimized for source data, often fail to predict target data when faced with distribution shifts (DSs). Previous benchmarking studies, though extensive, have mainly focused on simple DSs. Recognizing that DSs often occ ...

2025

Low-Rank Adaptation for Transformers in Dynamic Hand Gesture Recognition Using High-Density Surface Electromyography

Xingce Bao

Dynamic hand gesture recognition (HGR) is critical for real-time prosthetics and neural robotics applications, where high-density surface electromyography (HD-sEMG) signals provide valuable insights into muscle activity. However, adapting machine learning ...

IEEE2025

Advances in Algorithms for Sampling, Optimization and Inference in Disordered Systems

Giovanni Piccioli

This thesis focuses on the development of advanced algorithmic techniques, primarily Markov Chain Monte Carlo (MCMC) methods, and message passing algorithms, to tackle high-dimensional optimization and inference problems. The algorithms used have a probabi ...

EPFL2024

Neural decoding and feature selection methods for closed-loop control of avoidance behavior

Mahsa Shoaran, Jinhan Liu

Objective. Many psychiatric disorders involve excessive avoidant or defensive behavior, such as avoidance in anxiety and trauma disorders or defensive rituals in obsessive-compulsive disorders. Developing algorithms to predict these behaviors from local fi ...

IOP Publishing2024

Ground-based image deconvolution with Swin Transformer UNet

Frédéric Courbin, Pascale Jablonka, Utsav Akhaury

Aims. As ground-based all-sky astronomical surveys will gather millions of images in the coming years, a critical requirement emerges for the development of fast deconvolution algorithms capable of efficiently improving the spatial resolution of these imag ...

2024

Accelerated design of nickel-cobalt based catalysts for CO2 hydrogenation with human-in-the-loop active machine learning

Andreas Züttel, Yasemen Kuddusi

Thermo-catalytic conversion of CO2 into more valuable compounds, such as methane, is an attractive strategy for energy storage in chemical bonds and creating a carbon-based circular economy. However, designing heterogeneous catalysts remains a challenging, ...

2024

Optimal performance of Graph Convolutional Networks on the Contextual Stochastic Block Model

Patrick Thiran, Guillaume Cyprien Dalle

For Graph Neural Networks, oversmoothing denotes the homogenization of vertex embeddings as the number of layers increases. To better understand this phenomenon, we study community detection with a linearized Graph Convolutional Network on the Contextual S ...

2024

Nissl_1, Raw images for Machine learning for histological annotation and quantification of cortical layers

Julie Meystre

This dataset contains images (TIFF image data) of brain juvenile rats Wistar Han (P14) scanned immunostained slides by using an automated slide scanner (Olympus, VS120-L100, GER) equipped with a UPLSAPO 20x/0.75 air objective (Olympus, GER) and a Pike F5 ...

Zenodo2024

Solving Inverse PDE Problems using Grid-Free Monte Carlo Estimators

Ekrem Fatih Yilmazer, Wenzel Alban Jakob

Partial differential equations can model diverse physical phenomena including heat diffusion, incompressible flows, and electrostatic potentials. Given a description of an object's boundary and interior, traditional methods solve such PDEs by densely meshi ...

Association for Computing Machinery (ACM)2024

Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations

Volkan Cevher, Grigorios Chrysos, Igor Krawczuk, Justin Samuel Deschenaux

Denoising Diffusion Probabilistic Models (DDPMs) exhibit remarkable capabilities in image generation, with studies suggesting that they can generalize by composing latent factors learned from the training data. In this work, we go further and study DDPMs t ...

2024

On the modelling of the fatigue-induced damage in Francis turbines start-up sequences

Elena Vagnoni, Martin Seydoux, Ekaterina Krymova, Alessandro Morabito

The European Green Deal is prescribing a very ambitious rise in the annual production of renewable energy sources, and grid regulation services are increasingly important in the course of a massive integration of intermittent renewable energy sources. Alth ...

IOP Publishing2024

A methodology to optimize complex models in the context of nuclear waste repositories

Lyesse Laloui, Matthias Timothee Stanislas Wojnarowicz

With the increase in computational capabilities in recent decades, the possibility of modeling complex phenomena has continued to grow, inevitably increasing the number of calibrated parameters. Determining these parameters for complex coupled models can b ...

2024

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields: Processed data and trained models

Mathieu Salzmann, Alexander Mathis, Chen Zhao, Haozhe Qi

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields, CVPR 2024 Haozhe Qi, Chen Zhao, Mathieu Salzmann, Alexander Mathis. Affiliation: EPFL Date: June, 2024 Link to the CVPR article: https://openaccess.thecvf.com/conte ...

Zenodo2024

Enhancing spatial resolution in MÖNCH for electron microscopy via deep learning

Benjamin Bejar Haro, Luis Felipe Barba Flores, Carl Pierre Jacques Remlinger

However, their use in imaging applications has been limited by their relatively large pixel size (≥ 55 μm) and high-energy (>80 keV) electrons scattering over multiple pixels in the sensor layer. To realize the full potential of fast, radiation-hard HPDs a ...

2024

Multi-Label Generalized Zero Shot Chest X-Ray Classification by Combining Image-Text Information With Feature Disentanglement

Seyedbehzad Bozorgtabar

In fully supervised learning-based medical image classification, the robustness of a trained model depends on its exposure to various disease classes. Generalized Zero Shot Learning (GZSL) aims to predict both seen and novel unseen classes. While most GZSL ...

Institute of Electrical and Electronics Engineers2024

Learning sparse features can lead to overfitting in neural networks

Matthieu Wyart, Leonardo Petrini, Francesco Cagnetta

It is widely believed that the success of deep networks lies in their ability to learn a meaningful representation of the features of the data. Yet, understanding when and how this feature learning improves performance remains a challenge. For example, it ...

Iop Publishing Ltd2023