3.2k citations · 4.3k across the 27 of their papers we have counts for
30 papers
Can LLMs Reliably Annotate Bioassay Metadata to Improve Data Readiness?
Laura van Weesep, Riccardo Tedoldi, Jens Sjölund +6
The emergence of foundation models for molecular property prediction requires a high degree of AI data readiness, including reliable metadata annotation. However, both public repos…
To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation
Marc Botet Colomer, Pier Luigi Dovesi, Theodoros Panagiotakopoulos +6
The goal of Online Domain Adaptation for semantic segmentation is to handle unforeseeable domain changes that occur during deployment, like sudden weather events. However, the high…
Logistic-Normal Likelihoods for Heteroscedastic Label Noise
Erik Englesson, Amir Mehrpanah, Hossein Azizpour
A natural way of estimating heteroscedastic label noise in regression is to model the observed (potentially noisy) target as a sample from a normal distribution, whose parameters c…
On the Lipschitz Constant of Deep Networks and Double Descent
Matteo Gamba, Hossein Azizpour, Mårten Björkman
Existing bounds on the generalization error of deep networks assume some form of smooth or bounded dependence on the input variable, falling short of investigating the mechanisms c…
Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks
Miquel Martí i Rabadán, Alessandro Pieropan, Hossein Azizpour +1
We propose Dense FixMatch, a simple method for online semi-supervised learning of dense and structured prediction tasks combining pseudo-labeling and consistency regularization via…
Deep Double Descent via Smooth Interpolation
Matteo Gamba, Erik Englesson, Mårten Björkman +1
The ability of overparameterized deep networks to interpolate noisy data, while at the same time showing good generalization performance, has been recently characterized in terms o…
PatchDropout: Economizing Vision Transformers Using Patch Dropout
Yue Liu, Christos Matsoukas, Fredrik Strand +2
Vision transformers have demonstrated the potential to outperform CNNs in a variety of vision tasks. But the computational and memory requirements of these models prohibit their us…
Towards Self-Supervised Learning of Global and Object-Centric Representations
Federico Baldassarre, Hossein Azizpour
Self-supervision allows learning meaningful representations of natural images, which usually contain one central object. How well does it transfer to multi-entity scenes? We discus…
Are All Linear Regions Created Equal?
Matteo Gamba, Adrian Chmielewski-Anders, Josephine Sullivan +2
The number of linear regions has been studied as a proxy of complexity for ReLU networks. However, the empirical success of network compression techniques like pruning and knowledg…
An analysis of over-sampling labeled data in semi-supervised learning with FixMatch
Miquel Martí i Rabadán, Sebastian Bujwid, Alessandro Pieropan +2
Most semi-supervised learning methods over-sample labeled data when constructing training mini-batches. This paper studies whether this common practice improves learning and how. W…
CSAW-M: An Ordinal Classification Dataset for Benchmarking Mammographic Masking of Cancer
Moein Sorkhei, Yue Liu, Hossein Azizpour +6
Interval and large invasive breast cancers, which are associated with worse prognosis than other cancers, are usually detected at a late stage due to false negative assessments of…
Consistency Regularization Can Improve Robustness to Label Noise
Erik Englesson, Hossein Azizpour
Consistency regularization is a commonly-used technique for semi-supervised and self-supervised learning. It is an auxiliary objective function that encourages the prediction of th…
Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels
Erik Englesson, Hossein Azizpour
Prior works have found it beneficial to combine provably noise-robust loss functions e.g., mean absolute error (MAE) with standard categorical loss function e.g. cross entropy (CE)…
From coarse wall measurements to turbulent velocity fields through deep learning
Alejandro Güemes, Stefano Discetti, Andrea Ianiro +3
This work evaluates the applicability of super-resolution generative adversarial networks (SRGANs) as a methodology for the reconstruction of turbulent-flow quantities from coarse…
Explanation-based Weakly-supervised Learning of Visual Relations with Graph Networks
Federico Baldassarre, Kevin Smith, Josephine Sullivan +1
Visual relationship detection is fundamental for holistic image understanding. However, the localization and classification of (subject, predicate, object) triplets remain challeng…
Decoupling Inherent Risk and Early Cancer Signs in Image-based Breast Cancer Risk Models
Yue Liu, Hossein Azizpour, Fredrik Strand +1
The ability to accurately estimate risk of developing breast cancer would be invaluable for clinical decision-making. One promising new approach is to integrate image-based risk mo…
Recurrent neural networks and Koopman-based frameworks for temporal predictions in a low-order model of turbulence
Hamidreza Eivazi, Luca Guastoni, Philipp Schlatter +2
The capabilities of recurrent neural networks and Koopman-based frameworks are assessed in the prediction of temporal dynamics of the low-order model of near-wall turbulence by Moe…
Hyperplane Arrangements of Trained ConvNets Are Biased
Matteo Gamba, Stefan Carlsson, Hossein Azizpour +1
We investigate the geometric properties of the functions learned by trained ConvNets in the preactivation space of their convolutional layers, by performing an empirical study of h…
On the use of recurrent neural networks for predictions of turbulent flows
Luca Guastoni, Prem A. Srinivasan, Hossein Azizpour +2
In this paper, the prediction capabilities of recurrent neural networks are assessed in the low-order model of near-wall turbulence by Moehlis {\it et al.} (New J. Phys. {\bf 6}, 5…
Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation
Erik Englesson, Hossein Azizpour
In this work we aim to obtain computationally-efficient uncertainty estimates with deep networks. For this, we propose a modified knowledge distillation procedure that achieves sta…
Explainability Techniques for Graph Convolutional Networks
Federico Baldassarre, Hossein Azizpour
Graph Networks are used to make decisions in potentially complex scenarios but it is usually not obvious how or why they made them. In this work, we study the explainability of Gra…
Predictions of turbulent shear flows using deep neural networks
P. A. Srinivasan, L. Guastoni, H. Azizpour +2
In the present work we assess the capabilities of neural networks to predict temporally evolving turbulent flows. In particular, we use the nine-equation shear flow model by Moehli…
The role of artificial intelligence in achieving the Sustainable Development Goals
Ricardo Vinuesa, Hossein Azizpour, Iolanda Leite +7
The emergence of artificial intelligence (AI) and its progressively wider impact on many sectors across the society requires an assessment of its effect on sustainable development.…
GANtruth - an unpaired image-to-image translation method for driving scenarios
Sebastian Bujwid, Miquel Martí, Hossein Azizpour +1
Synthetic image translation has significant potentials in autonomous transportation systems. That is due to the expense of data collection and annotation as well as the unmanageabl…