1 code implementation • 13 Apr 2024 • Kateryna Chumachenko, Alexandros Iosifidis, Moncef Gabbouj
Within the field of multimodal DFER, recent methods have focused on exploiting advances of self-supervised learning (SSL) for pre-training of strong multimodal encoders.
Ranked #1 on Dynamic Facial Expression Recognition on MAFW
Dynamic Facial Expression Recognition Facial Expression Recognition +2
no code implementations • 27 Feb 2024 • Negar Heidari, Alexandros Iosifidis
Geometric Deep Learning techniques have become a transformative force in the field of Computer-Aided Design (CAD), and have the potential to revolutionize how designers and engineers approach and enhance the design process.
no code implementations • 19 Jan 2024 • Nan Li, Alexandros Iosifidis, Qi Zhang
To effectively trade-off communication, computation, and inference accuracy, we design a reward function and formulate the offloading problem of CNN inference as a maximization problem with the goal of maximizing the average inference accuracy and throughput over the long term.
no code implementations • 24 Nov 2023 • Mehdi Rafiei, Alexandros Iosifidis
In anomaly detection, identification of anomalies across diverse product categories is a complex task.
no code implementations • 16 Nov 2023 • Kateryna Chumachenko, Alexandros Iosifidis, Moncef Gabbouj
Interestingly, we also observe that optimization of the unimodal branches improves the multimodal branch, compared to a similar multimodal model trained from scratch.
no code implementations • 25 Oct 2023 • Mehdi Rafiei, Toby P. Breckon, Alexandros Iosifidis
Anomaly detection methods have demonstrated remarkable success across various applications.
no code implementations • 5 Oct 2023 • Martin Magris, Alexandros Iosifidis
The Bayesian estimation of GARCH-family models has been typically addressed through Monte Carlo sampling.
no code implementations • 2 Oct 2023 • Quoc Minh Nguyen, Dat Thanh Tran, Juho Kanniainen, Alexandros Iosifidis, Moncef Gabbouj
Many cryptocurrency brokers nowadays offer a variety of derivative assets that allow traders to perform hedging or speculation.
no code implementations • 25 Sep 2023 • Firas Laakom, Fahad Sohrab, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj
We show that such regularizers improve performance.
1 code implementation • 28 Jul 2023 • Amir Ramezani Dooraki, Alexandros Iosifidis
Curiosity is one of the main motives in many of the natural creatures with measurable levels of intelligence for exploration and, as a result, more efficient learning.
no code implementations • ICLR Workshop EBM 2021 • Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj
Energy-based learning is a powerful learning paradigm that encapsulates various discriminative and generative approaches.
1 code implementation • 24 May 2023 • Błażej Leporowski, Arian Bakhtiarnia, Nicole Bonnici, Adrian Muscat, Luca Zanella, Yiming Wang, Alexandros Iosifidis
We introduce the first audio-visual dataset for traffic anomaly detection taken from real-world scenes, called MAVAD, with a diverse range of weather and illumination conditions.
no code implementations • 22 May 2023 • Nan Li, Mehdi Bennis, Alexandros Iosifidis, Qi Zhang
This paper studies the computational offloading of video action recognition in edge computing.
no code implementations • 16 May 2023 • Arian Bakhtiarnia, Qi Zhang, Alexandros Iosifidis
The increasing prevalence of gigapixel resolutions has presented new challenges for crowd counting.
no code implementations • 23 Apr 2023 • Mehdi Rafiei, Alexandros Iosifidis
Using a discriminative representation obtained by supervised deep learning methods showed promising results on diverse Content-Based Image Retrieval (CBIR) problems.
no code implementations • 27 Mar 2023 • Christian Remi Wewer, Alexandros Iosifidis
Moisture content (MC) estimation is important in the manufacturing process of drying bulky filter media products as it is the prerequisite for drying optimization.
2 code implementations • 12 Feb 2023 • Illia Oleksiienko, Paraskevi Nousi, Nikolaos Passalis, Anastasios Tefas, Alexandros Iosifidis
Uncertainty estimation is an important task for critical problems, such as robotics and autonomous driving, because it allows creating statistically better perception models and signaling the model's certainty in its predictions to the decision method or a human supervisor.
2 code implementations • 12 Feb 2023 • Illia Oleksiienko, Alexandros Iosifidis
Autonomous driving needs to rely on high-quality 3D object detection to ensure safe navigation in the world.
no code implementations • 6 Feb 2023 • Morten From Elvebakken, Alexandros Iosifidis, Lukas Esterle
While this addresses limitations related to distributed data, it incurs a communication overhead as the model parameters or gradients need to be exchanged regularly during training.
no code implementations • 30 Jan 2023 • Arian Bakhtiarnia, Qi Zhang, Alexandros Iosifidis
In this paper, we introduce PromptMix, a method for artificially boosting the size of existing datasets, that can be used to improve the performance of lightweight networks.
no code implementations • 3 Jan 2023 • Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj
At each optimization step, neurons at a given layer receive feedback from neurons belonging to higher layers of the hierarchy.
no code implementations • 24 Nov 2022 • Andrea Cavagna, Nan Li, Alexandros Iosifidis, Qi Zhang
The proposed Edge Intelligence framework consists of the proposed effectiveness encoding and effectiveness decoding.
no code implementations • 24 Nov 2022 • Nan Li, Alexandros Iosifidis, Qi Zhang
We design a feature compression module based on the channel attention method in CNN, to compress the intermediate data by selecting the most important features.
no code implementations • 24 Nov 2022 • Zhongtian Dong, Nan Li, Alexandros Iosifidis, Qi Zhang
It is shown that the model selection with distributed inference HALP can significantly improve service reliability compared to the conventional stand-alone computation.
no code implementations • 21 Nov 2022 • Martin Magris, Alexandros Iosifidis
The last decade witnessed a growing interest in Bayesian learning.
1 code implementation • 17 Nov 2022 • Lukas Hedegaard, Aman Alok, Juby Jose, Alexandros Iosifidis
To improve on this, we propose Structured Pruning Adapters (SPAs), a family of compressing, task-switching network adapters, that accelerate and specialize networks using tiny parameter sets and structured pruning.
no code implementations • 10 Nov 2022 • Mehdi Rafiei, Jenni Raitoharju, Alexandros Iosifidis
X-ray imaging technology has been used for decades in clinical tasks to reveal the internal condition of different organs, and in recent years, it has become more common in other areas such as industry, security, and geography.
no code implementations • 1 Nov 2022 • Mehdi Rafiei, Dat Thanh Tran, Alexandros Iosifidis
Considering the low quantity of the dataset, cross-validation and augmentation methods are used during the training.
1 code implementation • 26 Oct 2022 • Martin Magris, Mostafa Shabani, Alexandros Iosifidis
We propose an optimization algorithm for Variational Inference (VI) in complex models.
no code implementations • 26 Oct 2022 • Mostafa Shabani, Martin Magris, George Tzagkarakis, Juho Kanniainen, Alexandros Iosifidis
Cross-correlation analysis is a powerful tool for understanding the mutual dynamics of time series.
no code implementations • 24 Oct 2022 • Nan Li, Alexandros Iosifidis, Qi Zhang
To solve the maximization problem, we propose a graph reinforcement learning-based early-exit mechanism (GRLE), which outperforms the state-of-the-art work, deep reinforcement learning-based online offloading (DROO) and its enhanced method, DROO with early-exit mechanism (DROOE), under different dynamic scenarios.
no code implementations • 17 Oct 2022 • Negar Heidari, Alexandros Iosifidis
Diversity of the features extracted by deep neural networks is important for enhancing the model generalization ability and accordingly its performance in different learning tasks.
Facial Expression Recognition Facial Expression Recognition (FER)
2 code implementations • 10 Oct 2022 • Illia Oleksiienko, Alexandros Iosifidis
Deep Ensembles, as a type of Bayesian Neural Networks, can be used to estimate uncertainty on the prediction of multiple neural networks by collecting votes from each network and computing the difference in those predictions.
no code implementations • 22 Sep 2022 • Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj
In this paper, we propose an approach that builds on top of BoF pooling to boost its efficiency by ensuring that the items of the learned dictionary are non-redundant.
no code implementations • 15 Aug 2022 • Arian Bakhtiarnia, Qi Zhang, Alexandros Iosifidis
JPEG image compression algorithm is a widely used technique for image size reduction in edge and cloud computing settings.
no code implementations • 11 Aug 2022 • Elizabeth Fons, Alejandro Sztrajman, Yousef El-Laham, Alexandros Iosifidis, Svitlana Vyetrenko
We show how these networks can be leveraged for the imputation of time series, with applications on both univariate and multivariate data.
no code implementations • 26 Jul 2022 • Arian Bakhtiarnia, Qi Zhang, Alexandros Iosifidis
Cameras in modern devices such as smartphones, satellites and medical equipment are capable of capturing very high resolution images and videos.
no code implementations • 23 Jul 2022 • Mostafa Shabani, Dat Thanh Tran, Juho Kanniainen, Alexandros Iosifidis
In addition, as the market evolves through time, it is necessary to update the existing models or train new ones when new data is made available.
no code implementations • 22 Jul 2022 • Nan Li, Alexandros Iosifidis, Qi Zhang
To reduce the computation time and communication overhead, we propose a novel collaborative edge computing using fused-layer parallelization to partition a CNN model into multiple blocks of convolutional layers.
no code implementations • 22 Jul 2022 • Nan Li, Alexandros Iosifidis, Qi Zhang
This paper studies inference acceleration using distributed convolutional neural networks (CNNs) in collaborative edge computing.
1 code implementation • 20 Jul 2022 • Arian Bakhtiarnia, Błażej Leporowski, Lukas Esterle, Alexandros Iosifidis
Images and video frames captured by cameras placed throughout smart cities are often transmitted over the network to a server to be processed by deep neural networks for various tasks.
3 code implementations • 4 Jul 2022 • Illia Oleksiienko, Dat Thanh Tran, Alexandros Iosifidis
Bayesian Neural Networks (BNNs) provide a tool to estimate the uncertainty of a neural network by considering a distribution over weights and sampling different models for each input.
2 code implementations • 6 Jun 2022 • Illia Oleksiienko, Paraskevi Nousi, Nikolaos Passalis, Anastasios Tefas, Alexandros Iosifidis
In this paper, we propose a novel voxel-based 3D single object tracking (3D SOT) method called Voxel Pseudo Image Tracking (VPIT).
no code implementations • 23 May 2022 • Arian Bakhtiarnia, Nemanja Milošević, Qi Zhang, Dragana Bajović, Alexandros Iosifidis
Split computing is a paradigm where a DNN is split into two sections; the first section is executed on the end device, and the output is transmitted to the edge server where the final section is executed.
no code implementations • 23 May 2022 • Martin Magris, Mostafa Shabani, Alexandros Iosifidis
Our Quasi Black-box Variational Inference (QBVI) framework is readily applicable to a wide class of Bayesian inference problems and is of simple implementation as the updates of the variational posterior do not involve gradients with respect to the model parameters, nor the prescription of the Fisher information matrix.
1 code implementation • 1 May 2022 • Jenni Raitoharju, Alexandros Iosifidis
Focusing on small-scale one-class classification, our analysis and experimental results show that the new formulation provides approaches to regularize, adjust the rank, and incorporate additional information into the kernel itself, leading to improved one-class classification accuracy.
1 code implementation • 7 Apr 2022 • Lukas Hedegaard, Alexandros Iosifidis
We present Continual Inference, a Python library for implementing Continual Inference Networks (CINs) in PyTorch, a class of Neural Networks designed specifically for efficient inference in both online and batch processing scenarios.
no code implementations • 5 Apr 2022 • Anssi Männistö, Mert Seker, Alexandros Iosifidis, Jenni Raitoharju
Applying machine learning tools to digitized image archives has a potential to revolutionize quantitative research of visual studies in humanities and social sciences.
1 code implementation • 21 Mar 2022 • Lukas Hedegaard, Negar Heidari, Alexandros Iosifidis
Graph-based reasoning over skeleton data has emerged as a promising approach for human action recognition.
Ranked #7 on Skeleton Based Action Recognition on Kinetics-Skeleton dataset (GFLOPS per prediction metric)
no code implementations • 7 Mar 2022 • Martin Magris, Mostafa Shabani, Alexandros Iosifidis
The prediction of financial markets is a challenging yet important task.
no code implementations • 10 Feb 2022 • Andreas Holm Nielsen, Alexandros Iosifidis, Henrik Karstoft
Classifying the state of the atmosphere into a finite number of large-scale circulation regimes is a popular way of investigating teleconnections, the predictability of severe weather events, and climate change.
no code implementations • 9 Feb 2022 • Firas Laakom, Jenni Raitoharju, Nikolaos Passalis, Alexandros Iosifidis, Moncef Gabbouj
In this paper, we consider the problem of non-linear dimensionality reduction under uncertainty, both from a theoretical and algorithmic perspectives.
no code implementations • 9 Feb 2022 • Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj
We tested our approach across different tasks: dimensionality reduction using three different dataset, image compression using the MNIST dataset, and image denoising using fashion MNIST.
no code implementations • 26 Jan 2022 • Kateryna Chumachenko, Alexandros Iosifidis, Moncef Gabbouj
In this work, we propose several attention formulations for multivariate sequence data.
1 code implementation • 26 Jan 2022 • Kateryna Chumachenko, Alexandros Iosifidis, Moncef Gabbouj
In this paper, we consider the problem of multimodal data analysis with a use case of audiovisual emotion recognition.
Ranked #1 on Facial Emotion Recognition on RAVDESS
1 code implementation • 17 Jan 2022 • Lukas Hedegaard, Arian Bakhtiarnia, Alexandros Iosifidis
Transformers in their common form are inherently limited to operate on whole token sequences rather than on one token at a time.
Ranked #4 on Online Action Detection on TVSeries
no code implementations • 14 Jan 2022 • Mostafa Shabani, Dat Thanh Tran, Martin Magris, Juho Kanniainen, Alexandros Iosifidis
Financial time-series forecasting is one of the most challenging domains in the field of time-series analysis.
no code implementations • 11 Jan 2022 • Rasmus Jensen, Alexandros Iosifidis
On the other hand, suspicious behavior flagging is characterized by non-disclosed features and hand-crafted risk indices.
1 code implementation • 10 Nov 2021 • Firas Laakom, Kateryna Chumachenko, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj
Based on this idea, we propose to reformulate the attention mechanism in CNNs to learn to ignore instead of learning to attend.
1 code implementation • 10 Nov 2021 • Firas Laakom, Jenni Raitoharju, Jarno Nikkanen, Alexandros Iosifidis, Moncef Gabbouj
We test this approach on the proposed method and show that it can indeed be used to avoid several extreme error cases and, thus, improves the practicality of the proposed technique.
1 code implementation • 2 Nov 2021 • Christian Møldrup Legaard, Thomas Schranz, Gerald Schweiger, Ján Drgoňa, Basak Falay, Cláudio Gomes, Alexandros Iosifidis, Mahdi Abkar, Peter Gorm Larsen
Dynamical systems see widespread use in natural sciences like physics, biology, chemistry, as well as engineering disciplines such as circuit analysis, computational fluid dynamics, and control.
1 code implementation • 30 Oct 2021 • Frederik Hvilshøj, Alexandros Iosifidis, Ira Assent
As counterfactual examples become increasingly popular for explaining decisions of deep learning models, it is essential to understand what properties quantitative evaluation metrics do capture and equally important what they do not capture.
no code implementations • 29 Sep 2021 • Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj
Neural networks are composed of multiple layers arranged in a hierarchical structure jointly trained with a gradient-based optimization, where the errors are back-propagated from the last layer back to the first one.
no code implementations • 21 Sep 2021 • Błażej Leporowski, Casper Hansen, Alexandros Iosifidis
Industrial processes are monitored by a large number of various sensors that produce time-series data.
no code implementations • 2 Sep 2021 • Dat Thanh Tran, Moncef Gabbouj, Alexandros Iosifidis
By developing compressive sensing and learning models that can operate with an adaptive compression rate, we can maximize the informational content throughput of the whole application.
1 code implementation • 1 Sep 2021 • Dat Thanh Tran, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis
Data normalization is one of the most important preprocessing steps when building a machine learning model, especially when the model of interest is a deep neural network.
no code implementations • 5 Jul 2021 • Błażej Leporowski, Daniella Tola, Casper Hansen, Alexandros Iosifidis
Detecting faults in manufacturing applications can be difficult, especially if each fault model is to be engineered by hand.
no code implementations • 5 Jul 2021 • Mostafa Shabani, Alexandros Iosifidis
Financial market analysis, especially the prediction of movements of stock prices, is a challenging problem.
no code implementations • 29 Jun 2021 • Arian Bakhtiarnia, Qi Zhang, Alexandros Iosifidis
In this work, we propose seven different architectures for early exit branches that can be used for dynamic inference in Vision Transformer backbones.
no code implementations • 16 Jun 2021 • Mert Seker, Anssi Männistö, Alexandros Iosifidis, Jenni Raitoharju
Identifying the main character in images plays an important role in traditional photographic studies and media analysis, but the task is performed manually and can be slow and laborious.
no code implementations • 10 Jun 2021 • Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj
We study the diversity of the features learned by a two-layer neural network trained with the least squares loss.
1 code implementation • 8 Jun 2021 • Negar Heidari, Alexandros Iosifidis
In this paper, we propose a method which learns an optimized compact network topology for real-time facial expression recognition utilizing localized facial landmark features.
Facial Expression Recognition Facial Expression Recognition (FER)
1 code implementation • 31 May 2021 • Lukas Hedegaard, Alexandros Iosifidis
We introduce Continual 3D Convolutional Neural Networks (Co3D CNNs), a new computational formulation of spatio-temporal 3D CNNs, in which videos are processed frame-by-frame rather than by clip.
Ranked #42 on Action Classification on Charades
1 code implementation • 21 May 2021 • Illia Oleksiienko, Alexandros Iosifidis
This means that the methods can achieve a speed-up of $40$-$60\%$ by restricting operation to near objects while not sacrificing much in performance.
no code implementations • 19 May 2021 • Arian Bakhtiarnia, Qi Zhang, Alexandros Iosifidis
Deploying deep learning models in time-critical applications with limited computational resources, for instance in edge computing systems and IoT networks, is a challenging task that often relies on dynamic inference methods such as early exiting.
1 code implementation • 29 Apr 2021 • Fahad Sohrab, Alexandros Iosifidis, Moncef Gabbouj, Jenni Raitoharju
In this paper, we propose a novel subspace learning framework for one-class classification.
no code implementations • 21 Apr 2021 • Arian Bakhtiarnia, Qi Zhang, Alexandros Iosifidis
Deploying deep learning services for time-sensitive and resource-constrained settings such as IoT using edge computing systems is a challenging task that requires dynamic adjustment of inference time.
1 code implementation • 31 Mar 2021 • Dat Thanh Tran, Moncef Gabbouj, Alexandros Iosifidis
Knowledge Distillation refers to a class of methods that transfers the knowledge from a teacher network to a student network.
1 code implementation • 25 Mar 2021 • Frederik Hvilshøj, Alexandros Iosifidis, Ira Assent
Counterfactual examples identify how inputs can be altered to change the predicted class of a classifier, thus opening up the black-box nature of, e. g., deep neural networks.
no code implementations • 12 Mar 2021 • Błażej Leporowski, Alexandros Iosifidis
Despite the popularisation of machine learning models, more often than not, they still operate as black boxes with no insight into what is happening inside the model.
1 code implementation • 11 Mar 2021 • Mert Seker, Anssi Männistö, Alexandros Iosifidis, Jenni Raitoharju
The World Health Organization (WHO) has provided guidelines on how to reduce the spread of the virus and one of the most important measures is social distancing.
no code implementations • 16 Feb 2021 • Elizabeth Fons, Paula Dawson, Xiao-jun Zeng, John Keane, Alexandros Iosifidis
Data augmentation methods have been shown to be a fundamental technique to improve generalization in tasks such as image, text and audio classification.
no code implementations • 9 Feb 2021 • Kateryna Chumachenko, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj
In this paper, we propose a method for ensembling the outputs of multiple object detectors for improving detection performance and precision of bounding boxes on image data.
no code implementations • 2 Feb 2021 • Błażej Leporowski, Daniella Tola, Casper Hansen, Alexandros Iosifidis
In order to do so, first a dataset that fully describes the operation of an industrial robot performing automated screwdriving must be available.
no code implementations • 1 Jan 2021 • Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj
During the last decade, neural networks have been intensively used to tackle various problems and they have often led to state-of-the-art results.
no code implementations • 23 Nov 2020 • Mohammad Soltanian, Junaid Malik, Jenni Raitoharju, Alexandros Iosifidis, Serkan Kiranyaz, Moncef Gabbouj
Automatic classification of speech commands has revolutionized human computer interactions in robotic applications.
no code implementations • 11 Nov 2020 • Negar Heidari, Alexandros Iosifidis
Graph convolutional networks (GCNs) have been very successful in skeleton-based human action recognition where the sequence of skeletons is modeled as a graph.
1 code implementation • 7 Nov 2020 • Negar Heidari, Alexandros Iosifidis
Graph convolutional networks (GCNs) achieved promising performance in skeleton-based human action recognition by modeling a sequence of skeletons as a spatio-temporal graph.
1 code implementation • 28 Oct 2020 • Elizabeth Fons, Paula Dawson, Xiao-jun Zeng, John Keane, Alexandros Iosifidis
Data augmentation methods in combination with deep neural networks have been used extensively in computer vision on classification tasks, achieving great success; however, their use in time series classification is still at an early stage.
no code implementations • 28 Oct 2020 • Elizabeth Fons, Paula Dawson, Xiao-jun Zeng, John Keane, Alexandros Iosifidis
In this paper we show that using transfer learning can help with this task, by pre-training a model to extract universal features on the full universe of stocks of the S$\&$P500 index and then transferring it to another model to directly learn a trading rule.
no code implementations • 23 Oct 2020 • Negar Heidari, Alexandros Iosifidis
In this paper, we propose a temporal attention module (TAM) for increasing the efficiency in skeleton-based action recognition by selecting the most informative skeletons of an action at the early layers of the network.
no code implementations • 22 Sep 2020 • Dat Thanh Tran, Moncef Gabbouj, Alexandros Iosifidis
Recently, the Multilinear Compressive Learning (MCL) framework was proposed to efficiently optimize the sensing and learning steps when working with multidimensional signals, i. e. tensors.
no code implementations • 1 Sep 2020 • Firas Laakom, Jenni Raitoharju, Nikolaos Passalis, Alexandros Iosifidis, Moncef Gabbouj
spectral-based subspace learning is a common data preprocessing step in many machine learning pipelines.
no code implementations • 21 Aug 2020 • Serkan Kiranyaz, Junaid Malik, Habib Ben Abdallah, Turker Ince, Alexandros Iosifidis, Moncef Gabbouj
As a heterogenous network model, ONNs are based on a generalized neuron model that can encapsulate any set of non-linear operators to boost diversity and to learn highly complex and multi-modal functions or spaces with minimal network complexity and training data.
no code implementations • 20 Jul 2020 • Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Jarno Nikkanen, Moncef Gabbouj
Computational color constancy is a preprocessing step used in many camera systems.
1 code implementation • 25 May 2020 • Dat Thanh Tran, Nikolaos Passalis, Anastasios Tefas, Moncef Gabbouj, Alexandros Iosifidis
In this paper, we propose 2D-Attention (2DA), a generic attention formulation for sequence data, which acts as a complementary computation block that can detect and focus on relevant sources of information for the given learning objective.
no code implementations • 6 May 2020 • Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Uygar Tuna, Jarno Nikkanen, Moncef Gabbouj
In this paper, we propose a novel unsupervised color constancy method, called Probabilistic Color Constancy (PCC).
2 code implementations • 24 Apr 2020 • Serkan Kiranyaz, Junaid Malik, Habib Ben Abdallah, Turker Ince, Alexandros Iosifidis, Moncef Gabbouj
However, Greedy Iterative Search (GIS) method, which is the search method used to find optimal operators in ONNs takes many training sessions to find a single operator set per layer.
1 code implementation • arXiv 2020 • Lukas Hedegaard, Omar Ali Sheikh-Omar, Alexandros Iosifidis
Domain Adaptation is the process of alleviating distribution gaps between data from different domains.
Ranked #27 on Domain Adaptation on Office-31
no code implementations • 8 Apr 2020 • Lei Xu, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj
The proposed method is based on a probabilistic model for defining the weights of individual samples in a weighted multi-label LDA approach.
1 code implementation • 27 Mar 2020 • Negar Heidari, Alexandros Iosifidis
Graph convolutional networks have been successful in addressing graph-based tasks such as semi-supervised node classification.
no code implementations • 25 Mar 2020 • Ali Senhaji, Jenni Raitoharju, Moncef Gabbouj, Alexandros Iosifidis
The most common approach in multi-domain learning is to form a domain agnostic model, the parameters of which are shared among all domains, and learn a small number of extra domain-specific parameters for each individual new domain.
1 code implementation • 20 Mar 2020 • Fahad Sohrab, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj
In this paper, we propose a novel method for transforming data into a low-dimensional space optimized for one-class classification.
1 code implementation • 9 Mar 2020 • Lukas Hedegaard Morsing, Omar Ali Sheikh-Omar, Alexandros Iosifidis
Getting deep convolutional neural networks to perform well requires a large amount of training data.
1 code implementation • 17 Feb 2020 • Dat Thanh Tran, Moncef Gabbouj, Alexandros Iosifidis
Progressive Neural Network Learning is a class of algorithms that incrementally construct the network's topology and optimize its parameters based on the training data.
1 code implementation • 17 Feb 2020 • Dat Thanh Tran, Moncef Gabbouj, Alexandros Iosifidis
Extensive experiments demonstrate that the proposed knowledge transfer method can effectively train MCL models to compressively sense and synthesize better features for the learning tasks with improved performances, especially when the complexity of the learning task increases.
no code implementations • 11 Feb 2020 • Kateryna Chumachenko, Jenni Raitoharju, Moncef Gabbouj, Alexandros Iosifidis
This paper proposes an incremental solution to Fast Subclass Discriminant Analysis (fastSDA).
no code implementations • 5 Feb 2020 • Johanna Ärje, Claus Melvad, Mads Rosenhøj Jeppesen, Sigurd Agerskov Madsen, Jenni Raitoharju, Maria Strandgård Rasmussen, Alexandros Iosifidis, Ville Tirronen, Kristian Meissner, Moncef Gabbouj, Toke Thomas Høye
We use this database to test the classification accuracy i. e. how well the species identity of a specimen can be predicted from images taken by the machine.
no code implementations • 31 Oct 2019 • William Lund Sommer, Alexandros Iosifidis
Visual concepts are determined by clustering the real image representations, and are subsequently used to evaluate the similarity of the generated images to the real ones by classifying them to the closest visual concept.
1 code implementation • 23 Oct 2019 • Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Jarno Nikkanen, Moncef Gabbouj
In this paper, we describe a new large dataset for illumination estimation.
Few-Shot Camera-Adaptive Color Constancy Image Declipping +1
no code implementations • 13 Aug 2019 • Jenni Raitoharju, Alexandros Iosifidis
In this paper, we carry out null space analysis for Class-Specific Discriminant Analysis (CSDA) and formulate a number of solutions based on the analysis.
no code implementations • 13 Jul 2019 • Adamantios Ntakaris, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis
Stock price prediction is a challenging task, but machine learning methods have recently been used successfully for this purpose.
1 code implementation • 11 Jun 2019 • Firas Laakom, Nikolaos Passalis, Jenni Raitoharju, Jarno Nikkanen, Anastasios Tefas, Alexandros Iosifidis, Moncef Gabbouj
To further improve the illumination estimation accuracy, we propose a novel attention mechanism for the BoCF model with two variants based on self-attention.
no code implementations • 4 Jun 2019 • Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Jarno Nikkanen, Moncef Gabbouj
In this paper, we study the importance of pre-training for the generalization capability in the color constancy problem.
2 code implementations • 17 May 2019 • Dat Thanh Tran, Mehmet Yamac, Aysen Degerli, Moncef Gabbouj, Alexandros Iosifidis
Compressive Learning is an emerging topic that combines signal acquisition via compressive sensing and machine learning to perform inference tasks directly on a small number of measurements.
1 code implementation • IEEE Transactions on Neural Networks and Learning Systems 2019 • Dat Thanh Tran, Alexandros Iosifidis, Juho Kanniainen, Moncef Gabbouj
Financial time-series forecasting has long been a challenging problem because of the inherently noisy and stochastic nature of the market.
1 code implementation • 2 May 2019 • Kateryna Chumachenko, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj
We show that by exploiting the structure of the between-class Laplacian matrix, the eigendecomposition step can be substituted with a much faster process.
1 code implementation • 22 Apr 2019 • Kateryna Chumachenko, Anssi Männistö, Alexandros Iosifidis, Jenni Raitoharju
In this paper, we demonstrate the benefits of using state-of-the-art machine learning methods in the analysis of historical photo archives.
1 code implementation • 16 Apr 2019 • Fahad Sohrab, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj
In this paper, we propose a novel method for projecting data from multiple modalities to a new subspace optimized for one-class classification.
no code implementations • 10 Apr 2019 • Adamantios Ntakaris, Giorgio Mirone, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis
Mid-price movement prediction based on limit order book (LOB) data is a challenging task due to the complexity and dynamics of the LOB.
no code implementations • 9 Apr 2019 • Junaid Malik, Serkan Kiranyaz, Riyadh Al-Raoush, Olivier Monga, Patricia Garnier, Sebti Foufou, Abdelaziz Bouras, Alexandros Iosifidis, Moncef Gabbouj, Philippe C. Baveye
Binary segmentation of volumetric images of porous media is a crucial step towards gaining a deeper understanding of the factors governing biogeochemical processes at minute scales.
no code implementations • 5 Mar 2019 • Dat Thanh Tran, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis
Forecasting based on financial time-series is a challenging task since most real-world data exhibits nonstationary property and nonlinear dependencies.
3 code implementations • 21 Feb 2019 • Nikolaos Passalis, Anastasios Tefas, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis
Deep Learning (DL) models can be used to tackle time series analysis tasks with great success.
no code implementations • 15 Feb 2019 • Serkan Kiranyaz, Turker Ince, Alexandros Iosifidis, Moncef Gabbouj
In order to address this drawback and also to accomplish a more generalized model over the convolutional neurons, this study proposes a novel network model, called Operational Neural Networks (ONNs), which can be heterogeneous and encapsulate neurons with any set of operators to boost diversity and to learn highly complex and multi-modal functions or spaces with minimal network complexity and training data.
no code implementations • 24 Jan 2019 • Nikolaos Passalis, Anastasios Tefas, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis
However, combining existing BoF formulations with deep feature extractors pose significant challenges: the distribution of the input features is not stationary, tuning the hyper-parameters of the model can be especially difficult and the normalizations involved in the BoF model can cause significant instabilities during the training process.
no code implementations • 14 Dec 2018 • Alexandros Iosifidis
The kernel matrix used in kernel methods encodes all the information required for solving complex nonlinear problems defined on data representations in the input space using simple, but implicitly defined, solutions.
no code implementations • 14 Dec 2018 • Alexandros Iosifidis
In this paper we formulate a probabilistic model for class-specific discriminant subspace learning.
no code implementations • 23 Oct 2018 • Avraam Tsantekidis, Nikolaos Passalis, Anastasios Tefas, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis
The recent surge in Deep Learning (DL) research of the past decade has successfully provided solutions to many difficult problems.
no code implementations • 19 Sep 2018 • Paraskevi Nousi, Avraam Tsantekidis, Nikolaos Passalis, Adamantios Ntakaris, Juho Kanniainen, Anastasios Tefas, Moncef Gabbouj, Alexandros Iosifidis
Forecasting the movements of stock prices is one the most challenging problems in financial markets analysis.
1 code implementation • 20 Aug 2018 • Dat Thanh Tran, Serkan Kiranyaz, Moncef Gabbouj, Alexandros Iosifidis
Generalized Operational Perceptron (GOP) was proposed to generalize the linear neuron model in the traditional Multilayer Perceptron (MLP) and this model can mimic the synaptic connections of the biological neurons that have nonlinear neurochemical behaviours.
no code implementations • 20 May 2018 • Chandan Gautam, Aruna Tiwari, Sundaram Suresh, Alexandros Iosifidis
In this paper, a multi-layer architecture (in a hierarchical fashion) by stacking various Kernel Ridge Regression (KRR) based Auto-Encoder for one-class classification is proposed and is referred as MKOC.
1 code implementation • 13 Apr 2018 • Dat Thanh Tran, Serkan Kiranyaz, Moncef Gabbouj, Alexandros Iosifidis
Previously, Generalized Operational Perceptron (GOP) was proposed to extend conventional perceptron model by defining a diverse set of neuronal activities to imitate a generalized model of biological neurons.
no code implementations • 19 Feb 2018 • Lei Xu, Alexandros Iosifidis, Moncef Gabbouj
In this paper, we propose a new variant of Linear Discriminant Analysis to overcome underlying drawbacks of traditional LDA and other LDA variants targeting problems involving imbalanced classes.
1 code implementation • 12 Feb 2018 • Fahad Sohrab, Jenni Raitoharju, Moncef Gabbouj, Alexandros Iosifidis
The method iteratively optimizes the data mapping along with data description in order to define a compact class representation in a low-dimensional feature space.
no code implementations • 31 Jan 2018 • Guanqun Cao, Alexandros Iosifidis, Moncef Gabbouj, Vijay Raghavan, Raju Gottumukkala
We study the problem of learning to rank from multiple information sources.
1 code implementation • 4 Dec 2017 • Dat Thanh Tran, Alexandros Iosifidis, Juho Kanniainen, Moncef Gabbouj
Financial time-series forecasting has long been a challenging problem because of the inherently noisy and stochastic nature of the market.
no code implementations • 29 Oct 2017 • Dat Thanh Tran, Moncef Gabbouj, Alexandros Iosifidis
There has been a great effort to transfer linear discriminant techniques that operate on vector data to high-order data, generally referred to as Multilinear Discriminant Analysis (MDA) techniques.
no code implementations • 28 Sep 2017 • Dat Thanh Tran, Alexandros Iosifidis, Moncef Gabbouj
The excellent performance of deep neural networks has enabled us to solve several automatization problems, opening an era of autonomous devices.
no code implementations • 5 Sep 2017 • Dat Thanh Tran, Martin Magris, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis
Nowadays, with the availability of massive amount of trade data collected, the dynamics of the financial markets pose both a challenge and an opportunity for high frequency traders.
no code implementations • 31 Aug 2017 • Guanqun Cao, Alexandros Iosifidis, Moncef Gabbouj
Face verification is a problem approached in the literature mainly using nonlinear class-specific subspace learning techniques.
no code implementations • 23 Aug 2017 • Johanna Ärje, Jenni Raitoharju, Alexandros Iosifidis, Ville Tirronen, Kristian Meissner, Moncef Gabbouj, Serkan Kiranyaz, Salme Kärkkäinen
Contrary to previous findings in the literature, we find that for machines following a typical flat classification approach commonly used in machine learning performs better than forcing machines to adopt a hierarchical, local per parent node approach used by human taxonomic experts ($\overline{CE}=13. 8\%$).
no code implementations • 13 Sep 2016 • Caglar Aytekin, Alexandros Iosifidis, Moncef Gabbouj
In this paper, we model the salient object detection problem under a probabilistic framework encoding the boundary connectivity saliency cue and smoothness constraints in an optimization problem.
no code implementations • 31 May 2016 • Guanqun Cao, Alexandros Iosifidis, Ke Chen, Moncef Gabbouj
In this paper, the problem of multi-view embedding from different visual cues and modalities is considered.