Publications related to Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics

Related publications (23)

Meteorological information prediction using images from webcams

Demetri Psaltis, Christophe Moser, Luisa Lambertini, Roy Sarkis

One aspect of the present invention proposes a method of predicting meteorological information by using an artificial deep neural network. The present invention according to one example focuses on image processing, specifically on fusing a plurality of ima ...

2025

Machine learning-aided hysteretic response prediction of double skin composite wall under earthquake loads

Yongtao Wu

Accurately and rapidly simulating the hysteretic behavior of double skin composite wall (DSCW) under earthquake loads enhance the efficiency of seismic performance assessments for high-rise steel-concrete composite structures. The application of artificial ...

2025

Automated processing of eXplainable Artificial Intelligence outputs in deep learning models for fault diagnostics of large infrastructures

Olga Fink

Deep Learning (DL) models processing images to recognize the health state of large infrastructure components can exhibit biases and rely on non-causal shortcuts. eXplainable Artificial Intelligence (XAI) can address these issues but manually analyzing expl ...

2025

Emotion information recovery potential of wav2vec2 network fine-tuned for speech recognition task

Tilak Purohit

Fine-tuning has become a norm to achieve state-of-the-art performance when employing pre-trained networks like foundation models. These models are typically pre-trained on large-scale unannotated data using self-supervised learning (SSL) methods. The SSL-b ...

Institute of Electrical and Electronics Engineers Inc.2025

Machine Learning-assisted Sustainable Mix Design of Waste Glass Powder Concrete with Strength-cost-co2 Emissions Trade-offs

Lei Xu

Glass powder, a non-degradable waste material, offers significant potential to reduce cement consumption and carbon emissions in concrete production. However, existing mix design methods for glass powder concrete (GPC) fail to systematically balance econom ...

MDPI2025

Self-Supervised Underwater Caustics Removal and Descattering via Deep Monocular SLAM

Devis Tuia, Jonathan Paul Sauder

Underwater scenes are challenging for computer vision methods due to color degradation caused by the water column and detrimental lighting effects such as caustic caused by sunlight refracting on a wavy surface. These challenges impede widespread use of co ...

Springer Nature (Switzerland)2024

Machine Understanding of Architectural Space: From Analytical to Generative Applications

Mikhael Johanes

The unprecedented development of machine learning (ML) and artificial intelligence (AI) has opened new ways of capturing architectural quality, where large neural networks have demonstrated remarkable capabilities compared to traditional rule-based approac ...

EPFL2024

VIVALDI: steel billet tracking with advanced computer vision

Liza Carol Andrea Dunbar

Our advanced computer vision system allows for the precise tracking of serial numbers on steel billets in challenging industrial settings. It combines cutting-edge hardware and machine learning, excelling in character recognition (99.8%) and localization w ...

SPIE2024

Pattern Formation in a Spiking Neural-Field of Renewal Neurons

Grégory Didier Dumont

Elucidating the neurophysiological mechanisms underlying neural pattern formation remains an outstanding challenge in Computational Neuroscience. In this paper, we address the issue of understanding the emergence of neural patterns by considering a network ...

2024

Second Edition Frcsyn Challenge at Cvpr 2024: Face Recognition Challenge in the Era of Synthetic Data

Alexander Carl Unnervik

Synthetic data is gaining increasing relevance for training machine learning models. This is mainly motivated due to several factors such as the lack of real data and intra-class variability, time and errors produced in manual labeling, and in some cases p ...

IEEE2024

Cross-Age and Cross-Site Domain Shift Impacts on Deep Learning-Based White Matter Fiber Estimation in Newborn and Baby Brains

Jean-Philippe Thiran, Meritxell Bach Cuadra, Rizhong Lin

Deep learning models have shown great promise in estimating tissue microstructure from limited diffusion magnetic resonance imaging data. However, these models face domain shift challenges when test and train data are from different scanners and protocols, ...

IEEE2024

On the Information in Deep Biometric Templates: from Vulnerability of Unprotected Templates to Leakage in Protected Templates

Hatef Otroshi Shahreza

Biometric recognition systems tend toward ubiquity and are widely being used in different applications for authentication purposes. Compared to conventional authentication tools, such as PIN or password, which are always in danger of being forgotten or sto ...

EPFL2024

Machine learning and its impact on psychiatric nosology: Findings from a qualitative study among German and Swiss experts

Georg Michael Joachim Starke

The increasing integration of Machine Learning (ML) techniques into clinical care, driven in particular by Deep Learning (DL) using Artificial Neural Nets (ANNs), promises to reshape medical practice on various levels and across multiple medical fields. Mu ...

2023

what If...? Pandemic Policy-decision-support to Guide a Cost-benefit-optimised, Country- Specific Response

Francesco Posa, Lucas Christophe Massemin, Giorgio Mannarini, Martin Jaggi, Mary-Anne Hartley, Tatjana Chavdarova, Prakhar Gupta, Thierry Bossy

Background After 18 months of responding to the COVID-19 pandemic, there is still no agreement on the optimal combination of mitigation strategies. The efficacy and collateral damage of pandemic policies are dependent on constantly evolving viral epidemiol ...

PUBLIC LIBRARY SCIENCE2022

ShapeNet: Shape constraint for galaxy image deconvolution

Utsav Akhaury

Deep learning (DL) has shown remarkable results in solving inverse problems in various domains. In particular, the Tikhonet approach is very powerful in deconvolving optical astronomical images. However, this approach only uses the l(2) loss, which does no ...

2022

MulT: An End-to-End Multitask Learning Transformer

Sabine Süsstrunk, Mathieu Salzmann, Tong Zhang, Deblina Bhattacharjee

We propose an end-to-end Multitask Learning Transformer framework, named MulT, to simultaneously learn multiple high-level vision tasks, including depth estimation, semantic segmentation, reshading, surface normal estimation, 2D keypoint detection, and edg ...

IEEE COMPUTER SOC2022

Bayesian Skip Net: Building on Prior Information for the Prediction and Segmentation of Stroke Lesions

Dimitri Nestor Alice Van De Ville, Maria Giulia Preti

Perfusion CT is widely used in acute ischemic stroke to determine eligibility for acute treatment, by defining an ischemic core and penumbra. In this work, we propose a novel way of building on prior information for the automatic prediction and segmentatio ...

SPRINGER INTERNATIONAL PUBLISHING AG2021

Non-Intrusive Reduced Order Modeling of Convection Dominated Flows Using Artificial Neural Networks with Application to Rayleigh-Taylor Instability

Jan Sickmann Hesthaven

A non-intrusive reduced order model (ROM) that combines a proper orthogonal decomposition (POD) and an artificial neural network (ANN) is primarily studied to investigate the applicability of the proposed ROM in recovering the solutions with shocks and str ...

GLOBAL SCIENCE PRESS2021

Data driven approximation of parametrized PDEs by reduced basis and neural networks

Simone Deparis, Luca Pegolotti, Niccolò Dal Santo

ACADEMIC PRESS INC ELSEVIER SCIENCE2020

Convergence without Convexity: Sampling, Optimization, and Games

Ya-Ping Hsieh

Many important problems in contemporary machine learning involve solving highly non- convex problems in sampling, optimization, or games. The absence of convexity poses significant challenges to convergence analysis of most training algorithms, and in some ...

EPFL2020