activity
20152023
most citedFastONN -- Python based open-source GPU implementation for Operational Neural Networks

24 citations · 105 across the 22 of their papers we have counts for

collaborators
Showing cs.CVShow all

16 papers · 1 filter

cs.CV2021

Remote Multilinear Compressive Learning with Adaptive Compression

Dat Thanh Tran, Moncef Gabbouj, Alexandros Iosifidis

Multilinear Compressive Learning (MCL) is an efficient signal acquisition and learning paradigm for multidimensional signals. The level of signal compression affects the detection…

cs.CV2021

BM3D vs 2-Layer ONN

Junaid Malik, Serkan Kiranyaz, Mehmet Yamac +1

Despite their recent success on image denoising, the need for deep and complex architectures still hinders the practical usage of CNNs. Older but computationally more efficient met…

cs.CV2021

Convolutional versus Self-Organized Operational Neural Networks for Real-World Blind Image Denoising

Junaid Malik, Serkan Kiranyaz, Mehmet Yamac +2

Real-world blind denoising poses a unique image restoration challenge due to the non-deterministic nature of the underlying noise distribution. Prevalent discriminative networks tr…

cs.CV2021

Ensembling object detectors for image and video data analysis

Kateryna Chumachenko, Jenni Raitoharju, Alexandros Iosifidis +1

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. We fur…

cs.CV2020

Performance Indicator in Multilinear Compressive Learning

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.…

cs.CV2020

Self-Organized Operational Neural Networks for Severe Image Restoration Problems

Junaid Malik, Serkan Kiranyaz, Moncef Gabbouj

Discriminative learning based on convolutional neural networks (CNNs) aims to perform image restoration by learning from training examples of noisy-clean image pairs. It has become…