Yannis Panagakis

Yannis Panagakis

Auto-generated profile, based on publicly available information

Yannis Panagakis

National and Kapodistrian University of Athens, National and Kapodistrian University of Athens, Athens, Attica, 10679, GREECE

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 April 2021 in Proceedings of the IEEE
Verified
Journal Article
Closed access
YPYannis Panagakis
Yannis Panagakis
JKJean Kossaifi
Jean Kossaifi
GCGrigorios G. Chrysos
Grigorios G. Chrysos
JOJames Oldfield
James Oldfield
MNMihalis A. Nicolaou
Mihalis A. Nicolaou
SZStefanos Zafeiriou
Stefanos Zafeiriou
Tensors, or multidimensional arrays, are data structures that can naturally represent visual data of multiple dimensions. Inherently able to efficiently capture structured, latent semantic spaces and high-order interactions, tensors have a long history of applications in a wide span of computer vision problems. With the advent of the deep learning paradigm shift in computer vision, tensors have become even more fundamental. Indeed, essential ingredients in modern deep learning architectures, such as convolutions and attention mechanisms, can readily be considered as tensor mappings. In effect, tensor methods are increasingly finding significant applications in deep learning, including the design of memory and compute efficient network architectures, improving robustness to random noise and adversarial attacks, and aiding the theoretical understanding of deep networks. This article provides an in-depth and practical review of tensors and tensor methods in the context of representation learning and deep learning, with a particular focus on visual data analysis and computer vision applications. Concretely, besides fundamental work in tensor-based visual data analysis methods, we focus on recent developments that have brought on a gradual increase in tensor methods, especially in deep learning architectures and their implications in computer vision applications. To further enable the newcomer to grasp such concepts quickly, we provide companion Python notebooks, covering key aspects of this article and implementing them, step-by-step with TensorLy.

15 May 2021 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
MGMarkos Georgopoulos
Markos Georgopoulos
JOJames Oldfield
James Oldfield
MNMihalis A. Nicolaou
Mihalis A. Nicolaou
YPYannis Panagakis
Yannis Panagakis
MPMaja Pantic
Maja Pantic
Deep learning has catalysed progress in tasks such as face recognition and analysis, leading to a quick integration of technological solutions in multiple layers of our society. While such systems have proven to be accurate by standard evaluation metrics and benchmarks, a surge of work has recently exposed the demographic bias that such algorithms exhibit–highlighting that accuracy does not entail fairness. Clearly, deploying biased systems under real-world settings can have grave consequences for affected populations. Indeed, learning methods are prone to inheriting, or even amplifying the bias present in a training set, manifested by uneven representation across demographic groups. In facial datasets, this particularly relates to attributes such as skin tone, gender, and age. In this work, we address the problem of mitigating bias in facial datasets by data augmentation. We propose a multi-attribute framework that can successfully transfer complex, multi-scale facial patterns even if these belong to underrepresented groups in the training set. This is achieved by relaxing the rigid dependence on a single attribute label, and further introducing a tensor-based mixing structure that captures multiplicative interactions between attributes in a multilinear fashion. We evaluate our method with an extensive set of qualitative and quantitative experiments on several datasets, with rigorous comparisons to state-of-the-art methods. We find that the proposed framework can successfully mitigate dataset bias, as evinced by extensive evaluations on established diversity metrics, while significantly improving fairness metrics such as equality of opportunity.

6 April 2023 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
KBKonstantinos Barmpas
Konstantinos Barmpas
YPYannis Panagakis
Yannis Panagakis
SBStylianos Bakas
Stylianos Bakas
DADimitrios Adamos
Dimitrios Adamos
NLNikolaos Laskaris
Nikolaos Laskaris
SZStefanos Zafeiriou
Stefanos Zafeiriou
Deep Convolutional Neural Networks (CNNs) have recently demonstrated impressive results in electroencephalogram (EEG) decoding for several Brain-Computer Interface (BCI) paradigms, including Motor-Imagery (MI). However, neurophysiological processes underpinning EEG signals vary across subjects causing covariate shifts in data distributions and hence hindering the generalization of deep models across subjects. In this paper, we aim to address the challenge of inter-subject variability in MI. To this end, we employ causal reasoning to characterize all possible distribution shifts in the MI task and propose a dynamic convolution framework to account for shifts caused by the inter-subject variability. Using publicly available MI datasets, we demonstrate improved generalization performance (up to 5%) across subjects in various MI tasks for four well-established deep architectures.

3 May 2024 in Journal of Neural Engineering
Verified
Journal Article
Open access
PDF file
KBKonstantinos Barmpas
Konstantinos Barmpas
YPYannis Panagakis
Yannis Panagakis
GZGeorgios Zoumpourlis
Georgios Zoumpourlis
DADimitrios Adamos
Dimitrios Adamos
NLNikolaos Laskaris
Nikolaos Laskaris
SZStefanos Zafeiriou
Stefanos Zafeiriou
Objective. Machine learning (ML) models have opened up enormous opportunities in the field of brain–computer Interfaces (BCIs). Despite their great success, they usually face severe limitations when they are employed in real-life applications outside a controlled laboratory setting. Approach. Mixing causal reasoning, identifying causal relationships between variables of interest, with brainwave modeling can change one’s viewpoint on some of these major challenges which can be found in various stages in the ML pipeline, ranging from data collection and data pre-processing to training methods and techniques. Main results. In this work, we employ causal reasoning and present a framework aiming to breakdown and analyze important challenges of brainwave modeling for BCIs. Significance. Furthermore, we present how general ML practices as well as brainwave-specific techniques can be utilized and solve some of these identified challenges. And finally, we discuss appropriate evaluation schemes in order to measure these techniques’ performance and efficiently compare them with other methods that will be developed in the future.

13 May 2024 in Journal of Neural Engineering
Verified
Journal Article
Open access
PDF file
SLSiegfried Ludwig
Siegfried Ludwig
SBStylianos Bakas
Stylianos Bakas
DADimitrios Adamos
Dimitrios Adamos
NLNikolaos Laskaris
Nikolaos Laskaris
YPYannis Panagakis
Yannis Panagakis
SZStefanos Zafeiriou
Stefanos Zafeiriou
Objective. The patterns of brain activity associated with different brain processes can be used to identify different brain states and make behavioural predictions. However, the relevant features are not readily apparent and accessible. Our aim is to design a system for learning informative latent representations from multichannel recordings of ongoing EEG activity. Approach: We propose a novel differentiable decoding pipeline consisting of learnable filters and a pre-determined feature extraction module. Specifically, we introduce filters parameterized by generalized Gaussian functions that offer a smooth derivative for stable end-to-end model training and allow for learning interpretable features. For the feature module, we use signal magnitude and functional connectivity estimates. Main results. We demonstrate the utility of our model on a new EEG dataset of unprecedented size (i.e. 721 subjects), where we identify consistent trends of music perception and related individual differences. Furthermore, we train and apply our model in two additional datasets, specifically for emotion recognition on SEED and workload classification on simultaneous task EEG workload. The discovered features align well with previous neuroscience studies and offer new insights, such as marked differences in the functional connectivity profile between left and right temporal areas during music listening. This agrees with the specialisation of the temporal lobes regarding music perception proposed in the literature. Significance. The proposed method offers strong interpretability of learned features while reaching similar levels of accuracy achieved by black box deep learning models. This improved trustworthiness may promote the use of deep learning models in real world applications. The model code is available at https://github.com/SMLudwig/EEGminer/.

22 September 2023 in Journal of Neural Engineering
Verified
Journal Article
Open access
KBKonstantinos Barmpas
Konstantinos Barmpas
YPYannis Panagakis
Yannis Panagakis
DADimitrios Adamos
Dimitrios Adamos
NLNikolaos Laskaris
Nikolaos Laskaris
SZStefanos Zafeiriou
Stefanos Zafeiriou
Objective. Brain–computer interfaces (BCIs) enable a direct communication of the brain with the external world, using one’s neural activity, measured by electroencephalography (EEG) signals. In recent years, convolutional neural networks (CNNs) have been widely used to perform automatic feature extraction and classification in various EEG-based tasks. However, their undeniable benefits are counterbalanced by the lack of interpretability properties as well as the inability to perform sufficiently when only limited amount of training data is available. Approach. In this work, we introduce a novel, lightweight, fully-learnable neural network architecture that relies on Gabor filters to delocalize EEG signal information into scattering decomposition paths along frequency and slow-varying temporal modulations. Main results. We utilize our network in two distinct modeling settings, for building either a generic (training across subjects) or a personalized (training within a subject) classifier. Significance. In both cases, using two different publicly available datasets and one in-house collected dataset, we demonstrate high performance for our model with considerably less number of trainable parameters as well as shorter training time compared to other state-of-the-art deep architectures. Moreover, our network demonstrates enhanced interpretability properties emerging at the level of the temporal filtering operation and enables us to train efficient personalized BCI models with limited amount of training data.