Search Results for author: Yannis Panagakis

Found 56 papers, 13 papers with code

Efficient Learning of Multiple NLP Tasks via Collective Weight Factorization on BERT

no code implementations Findings (NAACL) 2022 Christos Papadopoulos, Yannis Panagakis, Manolis Koubarakis, Mihalis Nicolaou

We test our proposed method on finetuning multiple natural language understanding tasks by employing BERT-Large as an instantiation of the Transformer and the GLUE as the evaluation benchmark.

Natural Language Understanding

Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization

1 code implementation19 Feb 2024 James Oldfield, Markos Georgopoulos, Grigorios G. Chrysos, Christos Tzelepis, Yannis Panagakis, Mihalis A. Nicolaou, Jiankang Deng, Ioannis Patras

The Mixture of Experts (MoE) paradigm provides a powerful way to decompose inscrutable dense layers into smaller, modular computations often more amenable to human interpretation, debugging, and editability.

Attribute counterfactual

Latent Alignment with Deep Set EEG Decoders

no code implementations29 Nov 2023 Stylianos Bakas, Siegfried Ludwig, Dimitrios A. Adamos, Nikolaos Laskaris, Yannis Panagakis, Stefanos Zafeiriou

We delineate a trade-off relationship between increased classification accuracy when alignment is performed at later modeling stages, and susceptibility to class-imbalance in the set of trials that the statistics are computed on.

Domain Adaptation EEG +2

Locality-preserving Directions for Interpreting the Latent Space of Satellite Image GANs

no code implementations26 Sep 2023 Georgia Kourmouli, Nikos Kostagiolas, Yannis Panagakis, Mihalis A. Nicolaou

We present a locality-aware method for interpreting the latent space of wavelet-based Generative Adversarial Networks (GANs), that can well capture the large spatial and spectral variability that is characteristic to satellite imagery.

Data Augmentation Scene Classification

Audio-visual video-to-speech synthesis with synthesized input audio

no code implementations31 Jul 2023 Triantafyllos Kefalas, Yannis Panagakis, Maja Pantic

The implicit assumption of this task is that the sound signal is either missing or contains a high amount of noise/corruption such that it is not useful for processing.

Speech Synthesis

Large-scale unsupervised audio pre-training for video-to-speech synthesis

no code implementations27 Jun 2023 Triantafyllos Kefalas, Yannis Panagakis, Maja Pantic

Most established approaches to date involve a two-step process, whereby an intermediate representation from the video, such as a spectrogram, is extracted first and then passed to a vocoder to produce the raw audio.

speech-recognition Speech Recognition +1

Parts of Speech-Grounded Subspaces in Vision-Language Models

2 code implementations23 May 2023 James Oldfield, Christos Tzelepis, Yannis Panagakis, Mihalis A. Nicolaou, Ioannis Patras

Latent image representations arising from vision-language models have proved immensely useful for a variety of downstream tasks.

Image Generation POS +1

Generalization analysis of an unfolding network for analysis-based Compressed Sensing

no code implementations9 Mar 2023 Vicky Kouni, Yannis Panagakis

Finally, the validity of our theory is assessed and numerical comparisons to a state-of-the-art unfolding network are made, on synthetic and real-world datasets.

Unsupervised Discovery of Semantic Concepts in Satellite Imagery with Style-based Wavelet-driven Generative Models

2 code implementations3 Aug 2022 Nikos Kostagiolas, Mihalis A. Nicolaou, Yannis Panagakis

In recent years, considerable advancements have been made in the area of Generative Adversarial Networks (GANs), particularly with the advent of style-based architectures that address many key shortcomings - both in terms of modeling capabilities and network interpretability.

Data Augmentation

PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs

1 code implementation31 May 2022 James Oldfield, Christos Tzelepis, Yannis Panagakis, Mihalis A. Nicolaou, Ioannis Patras

Recent advances in the understanding of Generative Adversarial Networks (GANs) have led to remarkable progress in visual editing and synthesis tasks, capitalizing on the rich semantics that are embedded in the latent spaces of pre-trained GANs.

Team Cogitat at NeurIPS 2021: Benchmarks for EEG Transfer Learning Competition

no code implementations1 Feb 2022 Stylianos Bakas, Siegfried Ludwig, Konstantinos Barmpas, Mehdi Bahri, Yannis Panagakis, Nikolaos Laskaris, Dimitrios A. Adamos, Stefanos Zafeiriou

The second task required to transfer models trained on the subjects of one or more source motor imagery datasets to perform inference on two target datasets, providing a small set of personalized calibration data for multiple test subjects.

EEG Eeg Decoding +1

Cluster-guided Image Synthesis with Unconditional Models

no code implementations CVPR 2022 Markos Georgopoulos, James Oldfield, Grigorios G Chrysos, Yannis Panagakis

The results highlight the ability of our approach to condition image generation on attributes like gender, pose and hair style on faces, as well as a variety of features on different object classes.

Image Generation

Tensor Component Analysis for Interpreting the Latent Space of GANs

no code implementations23 Nov 2021 James Oldfield, Markos Georgopoulos, Yannis Panagakis, Mihalis A. Nicolaou, Ioannis Patras

This paper addresses the problem of finding interpretable directions in the latent space of pre-trained Generative Adversarial Networks (GANs) to facilitate controllable image synthesis.

Image Generation

Defensive Tensorization

no code implementations26 Oct 2021 Adrian Bulat, Jean Kossaifi, Sourav Bhattacharya, Yannis Panagakis, Timothy Hospedales, Georgios Tzimiropoulos, Nicholas D Lane, Maja Pantic

We propose defensive tensorization, an adversarial defence technique that leverages a latent high-order factorization of the network.

Audio Classification Image Classification

EEGminer: Discovering Interpretable Features of Brain Activity with Learnable Filters

no code implementations19 Oct 2021 Siegfried Ludwig, Stylianos Bakas, Dimitrios A. Adamos, Nikolaos Laskaris, Yannis Panagakis, Stefanos Zafeiriou

Patterns of brain activity are associated with different brain processes and can be used to identify different brain states and make behavioral predictions.

EEG Eeg Decoding +1

Tensor Methods in Computer Vision and Deep Learning

no code implementations7 Jul 2021 Yannis Panagakis, Jean Kossaifi, Grigorios G. Chrysos, James Oldfield, Mihalis A. Nicolaou, Anima Anandkumar, Stefanos Zafeiriou

Tensors, or multidimensional arrays, are data structures that can naturally represent visual data of multiple dimensions.

Representation Learning

MVP: Multivariate polynomials for conditional generation

no code implementations1 Jan 2021 Grigorios Chrysos, Yannis Panagakis

The conditional variable can be discrete (e. g., a class label) or continuous (e. g., an input image) resulting into class-conditional (image) generation and image-to-image translation models, respectively.

Conditional Image Generation Image-to-Image Translation +1

Multilinear Latent Conditioning for Generating Unseen Attribute Combinations

no code implementations ICML 2020 Markos Georgopoulos, Grigorios Chrysos, Maja Pantic, Yannis Panagakis

Deep generative models rely on their inductive bias to facilitate generalization, especially for problems with high dimensional data, like images.

Attribute Inductive Bias

Deep Polynomial Neural Networks

3 code implementations20 Jun 2020 Grigorios Chrysos, Stylianos Moschoglou, Giorgos Bouritsas, Jiankang Deng, Yannis Panagakis, Stefanos Zafeiriou

We introduce three tensor decompositions that significantly reduce the number of parameters and show how they can be efficiently implemented by hierarchical neural networks.

Conditional Image Generation Face Identification +4

Enhancing Facial Data Diversity with Style-based Face Aging

no code implementations6 Jun 2020 Markos Georgopoulos, James Oldfield, Mihalis A. Nicolaou, Yannis Panagakis, Maja Pantic

By evaluating on several age-annotated datasets in both single- and cross-database experiments, we show that the proposed method outperforms state-of-the-art algorithms for age transfer, especially in the case of age groups that lie in the tails of the label distribution.

Data Augmentation

Investigating Bias in Deep Face Analysis: The KANFace Dataset and Empirical Study

no code implementations15 May 2020 Markos Georgopoulos, Yannis Panagakis, Maja Pantic

In this work, we investigate the demographic bias of deep learning models in face recognition, age estimation, gender recognition and kinship verification.

Age Estimation Face Recognition +1

$Π-$nets: Deep Polynomial Neural Networks

2 code implementations8 Mar 2020 Grigorios G. Chrysos, Stylianos Moschoglou, Giorgos Bouritsas, Yannis Panagakis, Jiankang Deng, Stefanos Zafeiriou

Deep Convolutional Neural Networks (DCNNs) is currently the method of choice both for generative, as well as for discriminative learning in computer vision and machine learning.

Audio Classification Graph Representation Learning +2

Defensive Tensorization: Randomized Tensor Parametrization for Robust Neural Networks

no code implementations25 Sep 2019 Adrian Bulat, Jean Kossaifi, Sourav Bhattacharya, Yannis Panagakis, Georgios Tzimiropoulos, Nicholas D. Lane, Maja Pantic

As deep neural networks become widely adopted for solving most problems in computer vision and audio-understanding, there are rising concerns about their potential vulnerability.

Adversarial Defense Audio Classification +1

PolyGAN: High-Order Polynomial Generators

no code implementations19 Aug 2019 Grigorios Chrysos, Stylianos Moschoglou, Yannis Panagakis, Stefanos Zafeiriou

Generative Adversarial Networks (GANs) have become the gold standard when it comes to learning generative models for high-dimensional distributions.

Vocal Bursts Intensity Prediction

Factorized Higher-Order CNNs with an Application to Spatio-Temporal Emotion Estimation

no code implementations CVPR 2020 Jean Kossaifi, Antoine Toisoul, Adrian Bulat, Yannis Panagakis, Timothy Hospedales, Maja Pantic

To alleviate this, one approach is to apply low-rank tensor decompositions to convolution kernels in order to compress the network and reduce its number of parameters.

Emotion Recognition Image Classification

Adversarial Learning of Disentangled and Generalizable Representations for Visual Attributes

1 code implementation9 Apr 2019 James Oldfield, Yannis Panagakis, Mihalis A. Nicolaou

Recently, a multitude of methods for image-to-image translation have demonstrated impressive results on problems such as multi-domain or multi-attribute transfer.

Attribute Image-to-Image Translation +1

Tensor Dropout for Robust Learning

no code implementations27 Feb 2019 Arinbjörn Kolbeinsson, Jean Kossaifi, Yannis Panagakis, Adrian Bulat, Anima Anandkumar, Ioanna Tzoulaki, Paul Matthews

CNNs achieve remarkable performance by leveraging deep, over-parametrized architectures, trained on large datasets.

Image Classification Inductive Bias

SEWA DB: A Rich Database for Audio-Visual Emotion and Sentiment Research in the Wild

no code implementations9 Jan 2019 Jean Kossaifi, Robert Walecki, Yannis Panagakis, Jie Shen, Maximilian Schmitt, Fabien Ringeval, Jing Han, Vedhas Pandit, Antoine Toisoul, Bjorn Schuller, Kam Star, Elnar Hajiyev, Maja Pantic

Natural human-computer interaction and audio-visual human behaviour sensing systems, which would achieve robust performance in-the-wild are more needed than ever as digital devices are increasingly becoming an indispensable part of our life.

Modeling of Facial Aging and Kinship: A Survey

no code implementations13 Feb 2018 Markos Georgopoulos, Yannis Panagakis, Maja Pantic

Computational facial models that capture properties of facial cues related to aging and kinship increasingly attract the attention of the research community, enabling the development of reliable methods for age progression, age estimation, age-invariant facial characterization, and kinship verification from visual data.

Age Estimation Kinship Verification

Side Information for Face Completion: a Robust PCA Approach

no code implementations20 Jan 2018 Niannan Xue, Jiankang Deng, Shiyang Cheng, Yannis Panagakis, Stefanos Zafeiriou

Robust principal component analysis (RPCA) is a powerful method for learning low-rank feature representation of various visual data.

Face Recognition Facial Inpainting +2

Visual Data Augmentation through Learning

no code implementations20 Jan 2018 Grigorios G. Chrysos, Yannis Panagakis, Stefanos Zafeiriou

In addition, the state-of-the-art data-driven methods demand a vast amount of data, hence a standard engineering trick employed is artificial data augmentation for instance by adding into the data cropped and (affinely) transformed images.

Data Augmentation

Robust Kronecker Component Analysis

no code implementations18 Jan 2018 Mehdi Bahri, Yannis Panagakis, Stefanos Zafeiriou

Dictionary learning and component analysis models are fundamental for learning compact representations that are relevant to a given task (feature extraction, dimensionality reduction, denoising, etc.).

Dictionary Learning Dimensionality Reduction +1

Multi-Attribute Robust Component Analysis for Facial UV Maps

no code implementations15 Dec 2017 Stylianos Moschoglou, Evangelos Ververas, Yannis Panagakis, Mihalis Nicolaou, Stefanos Zafeiriou

In this paper, we propose a novel component analysis technique that is suitable for facial UV maps containing a considerable amount of missing information and outliers, while additionally, incorporates knowledge from various attributes (such as age and identity).

3D Face Alignment Attribute +2

GAGAN: Geometry-Aware Generative Adversarial Networks

no code implementations CVPR 2018 Jean Kossaifi, Linh Tran, Yannis Panagakis, Maja Pantic

Deep generative models learned through adversarial training have become increasingly popular for their ability to generate naturalistic image textures.

Face Generation

An Adversarial Neuro-Tensorial Approach For Learning Disentangled Representations

no code implementations28 Nov 2017 Mengjiao Wang, Zhixin Shu, Shiyang Cheng, Yannis Panagakis, Dimitris Samaras, Stefanos Zafeiriou

Several factors contribute to the appearance of an object in a visual scene, including pose, illumination, and deformation, among others.

3D Face Reconstruction

Learning the Multilinear Structure of Visual Data

no code implementations CVPR 2017 Mengjiao Wang, Yannis Panagakis, Patrick Snape, Stefanos Zafeiriou

To extract these modes of variations from visual data, several supervised methods, such as the TensorFaces, that rely on multilinear (tensor) decomposition (e. g., Higher Order SVD) have been developed.

Tensor Decomposition

Robust Joint and Individual Variance Explained

no code implementations CVPR 2017 Christos Sagonas, Yannis Panagakis, Alina Leidinger, Stefanos Zafeiriou

Even though the CCA is a powerful tool, it has several drawbacks that render its application challenging for computer vision applications.

Robust Kronecker-Decomposable Component Analysis for Low-Rank Modeling

1 code implementation ICCV 2017 Mehdi Bahri, Yannis Panagakis, Stefanos Zafeiriou

In this paper, we introduce a new robust decomposition of images by combining ideas from sparse dictionary learning and PCP.

Dictionary Learning Image Denoising

Side Information in Robust Principal Component Analysis: Algorithms and Applications

no code implementations ICCV 2017 Niannan Xue, Yannis Panagakis, Stefanos Zafeiriou

Robust Principal Component Analysis (RPCA) aims at recovering a low-rank subspace from grossly corrupted high-dimensional (often visual) data and is a cornerstone in many machine learning and computer vision applications.

Facial Expression Recognition Facial Expression Recognition (FER) +1

3D Face Morphable Models "In-the-Wild"

no code implementations CVPR 2017 James Booth, Epameinondas Antonakos, Stylianos Ploumpis, George Trigeorgis, Yannis Panagakis, Stefanos Zafeiriou

In this paper, we propose the first, to the best of our knowledge, "in-the-wild" 3DMM by combining a powerful statistical model of facial shape, which describes both identity and expression, with an "in-the-wild" texture model.

Ranked #3 on 3D Face Reconstruction on Florence (Average 3D Error metric)

3D Face Reconstruction

Non-Negative Matrix Factorizations for Multiplex Network Analysis

no code implementations1 Dec 2016 Vladimir Gligorijevic, Yannis Panagakis, Stefanos Zafeiriou

Networks have been a general tool for representing, analyzing, and modeling relational data arising in several domains.

Clustering Community Detection

TensorLy: Tensor Learning in Python

1 code implementation29 Oct 2016 Jean Kossaifi, Yannis Panagakis, Anima Anandkumar, Maja Pantic

In addition, using the deep-learning frameworks as backend allows users to easily design and train deep tensorized neural networks.

Robust Statistical Face Frontalization

no code implementations ICCV 2015 Christos Sagonas, Yannis Panagakis, Stefanos Zafeiriou, Maja Pantic

The proposed method is assessed in frontal face reconstruction, face landmark localization, pose-invariant face recognition, and face verification in unconstrained conditions.

Face Alignment Face Recognition +3

Face Flow

no code implementations ICCV 2015 Patrick Snape, Anastasios Roussos, Yannis Panagakis, Stefanos Zafeiriou

In this paper, we propose a method for the robust and efficient computation of multi-frame optical flow in an expressive sequence of facial images.

Optical Flow Estimation

Automatic Construction Of Robust Spherical Harmonic Subspaces

no code implementations CVPR 2015 Patrick Snape, Yannis Panagakis, Stefanos Zafeiriou

In this paper we propose a method to automatically recover a class specific low dimensional spherical harmonic basis from a set of in-the-wild facial images.

Face frontalization for Alignment and Recognition

no code implementations3 Feb 2015 Christos Sagonas, Yannis Panagakis, Stefanos Zafeiriou, Maja Pantic

The proposed method is assessed in frontal face reconstruction (pose correction), face landmark localization, and pose-invariant face recognition and verification by conducting experiments on $6$ facial images databases.

Face Recognition Face Reconstruction +1

RAPS: Robust and Efficient Automatic Construction of Person-Specific Deformable Models

no code implementations CVPR 2014 Christos Sagonas, Yannis Panagakis, Stefanos Zafeiriou, Maja Pantic

Next, to correct the fittings of a generic model, image congealing (i. e., batch image aliment) is performed by employing only the learnt orthonormal subspace.

Face Alignment Image Reconstruction

Robust Canonical Time Warping for the Alignment of Grossly Corrupted Sequences

no code implementations CVPR 2013 Yannis Panagakis, Mihalis A. Nicolaou, Stefanos Zafeiriou, Maja Pantic

The superiority of the proposed method against the state-of-the-art time alignment methods, namely the canonical time warping and the generalized time warping, is indicated by the experimental results on both synthetic and real datasets.

Compressive Sensing Dynamic Time Warping

Cannot find the paper you are looking for? You can Submit a new open access paper.