no code implementations • 18 May 2024 • Emmanouil Maragkoudakis, Symeon Papadopoulos, Iraklis Varlamis, Christos Diou
To mitigate bias, we propose two alternative methods for sampling on selected lines or spheres of the latent space to increase the number of generated samples from the under-represented classes.
1 code implementation • 3 Apr 2024 • Vasilis Gkolemis, Christos Diou, Eirini Ntoutsi, Theodore Dalamagas, Bernd Bischl, Julia Herbinger, Giuseppe Casalicchio
Effector implements well-established global effect methods, assesses the heterogeneity of each method and, based on that, provides regional effects.
no code implementations • 31 Mar 2024 • Niki Kiriakidou, Ioannis E. Livieris, Christos Diou
Causal effect estimation aims at estimating the Average Treatment Effect as well as the Conditional Average Treatment Effect of a treatment to an outcome from the available data.
1 code implementation • 1 Dec 2023 • Aristotelis Ballas, Vasileios Papapanagiotou, Christos Diou
Despite the recent increase in research activity, deep-learning models have not yet been widely accepted in several real-world settings, such as medicine.
1 code implementation • 17 Nov 2023 • Pietro Melzi, Ruben Tolosana, Ruben Vera-Rodriguez, Minchul Kim, Christian Rathgeb, Xiaoming Liu, Ivan DeAndres-Tame, Aythami Morales, Julian Fierrez, Javier Ortega-Garcia, Weisong Zhao, Xiangyu Zhu, Zheyu Yan, Xiao-Yu Zhang, Jinlin Wu, Zhen Lei, Suvidha Tripathi, Mahak Kothari, Md Haider Zama, Debayan Deb, Bernardo Biesseck, Pedro Vidal, Roger Granada, Guilherme Fickel, Gustavo Führ, David Menotti, Alexander Unnervik, Anjith George, Christophe Ecabert, Hatef Otroshi Shahreza, Parsa Rahimi, Sébastien Marcel, Ioannis Sarridis, Christos Koutlis, Georgia Baltsou, Symeon Papadopoulos, Christos Diou, Nicolò Di Domenico, Guido Borghi, Lorenzo Pellegrini, Enrique Mas-Candela, Ángela Sánchez-Pérez, Andrea Atzori, Fadi Boutros, Naser Damer, Gianni Fenu, Mirko Marras
Despite the widespread adoption of face recognition technology around the world, and its remarkable performance on current benchmarks, there are still several challenges that must be covered in more detail.
no code implementations • 21 Sep 2023 • Vasilis Gkolemis, Anargiros Tzerefos, Theodore Dalamagas, Eirini Ntoutsi, Christos Diou
Consequently, RAMs fit one component per subregion of each feature instead of one component per feature.
1 code implementation • 20 Sep 2023 • Vasilis Gkolemis, Theodore Dalamagas, Eirini Ntoutsi, Christos Diou
RHALE quantifies the heterogeneity by considering the standard deviation of the local effects and automatically determines an optimal variable-size bin-splitting.
1 code implementation • 28 Aug 2023 • Aristotelis Ballas, Christos Diou
During the past decade, deep neural networks have led to fast-paced progress and significant achievements in computer vision problems, for both academia and industry.
no code implementations • 6 Aug 2023 • Anastasios Iliopoulos, John Violos, Christos Diou, Iraklis Varlamis
To boost the performance of these base models, we propose a feature-bagging technique that considers only a subset of features at a time, and we further apply a transformation that is based on nested rotation computed from Principal Component Analysis (PCA) to improve the effectiveness and generalization of the approach.
no code implementations • 19 Jul 2023 • Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
This paper presents an in-depth analysis, with a particular emphasis on the intersectionality of these demographic factors.
no code implementations • 26 May 2023 • Aristotelis Ballas, Christos Diou
In search of robust and generalizable machine learning models, Domain Generalization (DG) has gained significant traction during the past few years.
no code implementations • 11 May 2023 • Niki Kiriakidou, Christos Diou
The proposed NNCI methodology is applied to some of the most well established neural network-based models for treatment effect estimation with the use of observational data.
1 code implementation • 27 Apr 2023 • Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
To overcome these limitations, this work introduces FLAC, a methodology that minimizes mutual information between the features extracted by the model and a protected attribute, without the use of attribute labels.
Ranked #1 on HairColor/Bias-conflicting on CelebA
no code implementations • 2 Apr 2023 • Aristotelis Ballas, Christos Diou
In the present work, we focus on this problem of Domain Generalization and propose an alternative neural network architecture for robust, out-of-distribution image classification.
1 code implementation • 20 Mar 2023 • Aristotelis Ballas, Christos Diou
Our objective in this work is to propose a benchmark for evaluating DG algorithms, in addition to introducing a novel architecture for tackling DG in biosignal classification.
no code implementations • 27 Oct 2022 • Panagiotis Rizomiliotis, Christos Diou, Aikaterini Triakosia, Ilias Kyrannas, Konstantinos Tserpes
Oblivious inference is the task of outsourcing a ML model, like neural-networks, without disclosing critical and sensitive information, like the model's parameters.
1 code implementation • 10 Oct 2022 • Vasilis Gkolemis, Theodore Dalamagas, Christos Diou
In this paper, we propose a novel ALE approximation, called Differential Accumulated Local Effects (DALE), which can be used in cases where the ML model is differentiable and an auto-differentiable framework is accessible.
no code implementations • 31 Aug 2022 • Aristotelis Ballas, Vasileios Papapanagiotou, Anastasios Delopoulos, Christos Diou
The PhysioNet 2022 challenge targets automatic detection of murmur from audio recordings of the heart and automatic detection of normal vs. abnormal clinical outcome.
no code implementations • 31 Aug 2022 • Niki Kiriakidou, Christos Diou
In this paper, we propose to complement the evaluation of causal inference models using concrete statistical evidence, including the performance profiles of Dolan and Mor{\'e}, as well as non-parametric and post-hoc statistical tests.
no code implementations • 20 Aug 2022 • Aristotelis Ballas, Christos Diou
Deep Learning systems have achieved great success in the past few years, even surpassing human intelligence in several cases.
no code implementations • 27 Jul 2022 • Aristotelis Ballas, Christos Diou
Convolutional Neural Networks have become the norm in image classification.
no code implementations • 4 Jun 2022 • Christos Diou, Konstantinos Kyritsis, Vasileios Papapanagiotou, Ioannis Sarafis
The progress in artificial intelligence and machine learning algorithms over the past decade has enabled the development of new methods for the objective measurement of eating, including both the measurement of eating episodes as well as the measurement of in-meal eating behavior.
no code implementations • 23 May 2022 • Niki Kiriakidou, Christos Diou
Nowadays, in many scientific and industrial fields there is an increasing need for estimating treatment effects and answering causal questions.
1 code implementation • 2 Aug 2021 • Vasileios Papapanagiotou, Christos Diou, Anastasios Delopoulos
A common bottleneck for developing and training machine learning algorithms is obtaining labeled data for training supervised algorithms, and in particular ground truth annotations.
no code implementations • 20 May 2021 • Vasileios Papapanagiotou, Christos Diou, Janet van den Boer, Monica Mars, Anastasios Delopoulos
Our approach performs very well in recognizing crispiness (0. 95 weighted accuracy on new subjects and 0. 93 on new food types) and demonstrates promising results for objective and automatic recognition of wetness and chewiness.
no code implementations • 12 Oct 2020 • Konstantinos Kyritsis, Christos Diou, Anastasios Delopoulos
The increased worldwide prevalence of obesity has sparked the interest of the scientific community towards tools that objectively and automatically monitor eating behavior.
no code implementations • 17 Sep 2018 • Ioannis Sarafis, Christos Diou, Anastasios Delopoulos
Experiments on 14 benchmark data sets and data sets with importance scores for the training instances show that: (a) the condition for the existence of span in weighted SVM is satisfied almost always; (b) the span-rule is the most effective method for weighted SVM hyperparameter selection; (c) the span-rule is the best predictor of the test error in the mean square error sense; and (d) the span-rule is efficient and, for certain problems, it can be calculated faster than $K$-fold cross-validation.
no code implementations • 26 Jun 2017 • Angelos Katharopoulos, Despoina Paschalidou, Christos Diou, Anastasios Delopoulos
This paper introduces a family of local feature aggregation functions and a novel method to estimate their parameters, such that they generate optimal representations for classification (or any task that can be expressed as a cost function minimization problem).