Search Results for author: Anastasios Tefas

Found 20 papers, 9 papers with code

VPIT: Real-time Embedded Single Object 3D Tracking Using Voxel Pseudo Images

2 code implementations6 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).

Object Tracking

Deep Residual Error and Bag-of-Tricks Learning for Gravitational Wave Surrogate Modeling

no code implementations16 Mar 2022 Styliani-Christina Fragkouli, Paraskevi Nousi, Nikolaos Passalis, Panagiotis Iosif, Nikolaos Stergioulas, Anastasios Tefas

Deep learning methods have been employed in gravitational-wave astronomy to accelerate the construction of surrogate waveforms for the inspiral of spin-aligned black hole binaries, among other applications.


Quadratic mutual information regularization in real-time deep CNN models

no code implementations26 Aug 2021 Maria Tzelepi, Anastasios Tefas

In this paper, regularized lightweight deep convolutional neural network models, capable of effectively operating in real-time on devices with restricted computational power for high-resolution video input are proposed.

Efficient training of lightweight neural networks using Online Self-Acquired Knowledge Distillation

no code implementations26 Aug 2021 Maria Tzelepi, Anastasios Tefas

Knowledge Distillation has been established as a highly promising approach for training compact and faster models by transferring knowledge from heavyweight and powerful models.

Density Estimation Knowledge Distillation

Semantic Scene Segmentation for Robotics Applications

no code implementations25 Aug 2021 Maria Tzelepi, Anastasios Tefas

Semantic scene segmentation plays a critical role in a wide range of robotics applications, e. g., autonomous navigation.

Autonomous Navigation Scene Segmentation

Autoencoder-driven Spiral Representation Learning for Gravitational Wave Surrogate Modelling

no code implementations9 Jul 2021 Paraskevi Nousi, Styliani-Christina Fragkouli, Nikolaos Passalis, Panagiotis Iosif, Theocharis Apostolatos, George Pappas, Nikolaos Stergioulas, Anastasios Tefas

Based on this finding, we design a spiral module with learnable parameters, that is used as the first layer in a neural network, which learns to map the input space to the coefficients.

Astronomy Representation Learning

Attention-based Neural Bag-of-Features Learning for Sequence Data

1 code implementation25 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.

Medical Diagnosis

Heterogeneous Knowledge Distillation using Information Flow Modeling

1 code implementation CVPR 2020 Nikolaos Passalis, Maria Tzelepi, Anastasios Tefas

The proposed method is capable of overcoming the aforementioned limitations by using an appropriate supervision scheme during the different phases of the training process, as well as by designing and training an appropriate auxiliary teacher model that acts as a proxy model capable of "explaining" the way the teacher works to the student.

Knowledge Distillation

Bag of Color Features For Color Constancy

1 code implementation11 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.

Color Constancy

Temporal Logistic Neural Bag-of-Features for Financial Time series Forecasting leveraging Limit Order Book Data

no code implementations24 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.

Density Estimation Time Series Analysis +1

Deep Supervised Hashing leveraging Quadratic Spherical Mutual Information for Content-based Image Retrieval

no code implementations16 Jan 2019 Nikolaos Passalis, Anastasios Tefas

The proposed method is adapted to the needs of large-scale hashing and information retrieval leading to a novel information-theoretic measure, the Quadratic Spherical Mutual Information (QSMI).

Content-Based Image Retrieval Information Retrieval

Style Decomposition for Improved Neural Style Transfer

no code implementations30 Nov 2018 Paraskevas Pegios, Nikolaos Passalis, Anastasios Tefas

Universal Neural Style Transfer (NST) methods are capable of performing style transfer of arbitrary styles in a style-agnostic manner via feature transforms in (almost) real-time.

Style Transfer

Interactive dimensionality reduction using similarity projections

no code implementations13 Nov 2018 Dimitris Spathis, Nikolaos Passalis, Anastasios Tefas

In order to visualize that data in 2D or 3D, usually Dimensionality Reduction (DR) techniques are employed.

Dimensionality Reduction Domain Adaptation

Decoding Generic Visual Representations From Human Brain Activity using Machine Learning

1 code implementation5 Nov 2018 Angeliki Papadimitriou, Nikolaos Passalis, Anastasios Tefas

Among the most impressive recent applications of neural decoding is the visual representation decoding, where the category of an object that a subject either sees or imagines is inferred by observing his/her brain activity.

BIG-bench Machine Learning

Using Deep Learning for price prediction by exploiting stationary limit order book features

no code implementations23 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.

Time Series

Learning Deep Representations with Probabilistic Knowledge Transfer

1 code implementation ECCV 2018 Nikolaos Passalis, Anastasios Tefas

Knowledge Transfer (KT) techniques tackle the problem of transferring the knowledge from a large and complex neural network into a smaller and faster one.

General Classification Representation Learning +1

Learning Bag-of-Features Pooling for Deep Convolutional Neural Networks

2 code implementations ICCV 2017 Nikolaos Passalis, Anastasios Tefas

Convolutional Neural Networks (CNNs) are well established models capable of achieving state-of-the-art classification accuracy for various computer vision tasks.

General Classification Quantization

Dimensionality Reduction using Similarity-induced Embeddings

1 code implementation18 Jun 2017 Nikolaos Passalis, Anastasios Tefas

The vast majority of Dimensionality Reduction (DR) techniques rely on second-order statistics to define their optimization objective.

Supervised dimensionality reduction

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