65 citations · 287 across the 27 of their papers we have counts for
14 papers · 1 filter
Deep Active Perception for Object Detection using Navigation Proposals
Stefanos Ginargiros, Nikolaos Passalis, Anastasios Tefas
Deep Learning (DL) has brought significant advances to robotics vision tasks. However, most existing DL methods have a major shortcoming, they rely on a static inference paradigm i…
Variational Voxel Pseudo Image Tracking
Illia Oleksiienko, Paraskevi Nousi, Nikolaos Passalis +2
Uncertainty estimation is an important task for critical problems, such as robotics and autonomous driving, because it allows creating statistically better perception models and si…
A Novel Dataset for Evaluating and Alleviating Domain Shift for Human Detection in Agricultural Fields
Paraskevi Nousi, Emmanouil Mpampis, Nikolaos Passalis +2
In this paper we evaluate the impact of domain shift on human detection models trained on well known object detection datasets when deployed on data outside the distribution of the…
VPIT: Real-time Embedded Single Object 3D Tracking Using Voxel Pseudo Images
Illia Oleksiienko, Paraskevi Nousi, Nikolaos Passalis +2
In this paper, we propose a novel voxel-based 3D single object tracking (3D SOT) method called Voxel Pseudo Image Tracking (VPIT). VPIT is the first method that uses voxel pseudo i…
Efficient training of lightweight neural networks using Online Self-Acquired Knowledge Distillation
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. Ho…
Quadratic mutual information regularization in real-time deep CNN models
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 hi…
Semantic Scene Segmentation for Robotics Applications
Maria Tzelepi, Anastasios Tefas
Semantic scene segmentation plays a critical role in a wide range of robotics applications, e.g., autonomous navigation. These applications are accompanied by specific computationa…
Heterogeneous Knowledge Distillation using Information Flow Modeling
Nikolaos Passalis, Maria Tzelepi, Anastasios Tefas
Knowledge Distillation (KD) methods are capable of transferring the knowledge encoded in a large and complex teacher into a smaller and faster student. Early methods were usually l…
Bag of Color Features For Color Constancy
Firas Laakom, Nikolaos Passalis, Jenni Raitoharju +4
In this paper, we propose a novel color constancy approach, called Bag of Color Features (BoCF), building upon Bag-of-Features pooling. The proposed method substantially reduces th…
Deep Supervised Hashing leveraging Quadratic Spherical Mutual Information for Content-based Image Retrieval
Nikolaos Passalis, Anastasios Tefas
Several deep supervised hashing techniques have been proposed to allow for efficiently querying large image databases. However, deep supervised image hashing techniques are develop…
Style Decomposition for Improved Neural Style Transfer
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.…
Interactive dimensionality reduction using similarity projections
Dimitris Spathis, Nikolaos Passalis, Anastasios Tefas
Recent advances in machine learning allow us to analyze and describe the content of high-dimensional data like text, audio, images or other signals. In order to visualize that data…
Learning Bag-of-Features Pooling for Deep Convolutional Neural Networks
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. However, they are…
Dimensionality Reduction using Similarity-induced Embeddings
Nikolaos Passalis, Anastasios Tefas
The vast majority of Dimensionality Reduction (DR) techniques rely on second-order statistics to define their optimization objective. Even though this provides adequate results in…