Search Results for author: Firas Laakom

Found 15 papers, 4 papers with code

Efficient CNN with uncorrelated Bag of Features pooling

no code implementations22 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.

Non-Linear Spectral Dimensionality Reduction Under Uncertainty

no code implementations9 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.

Dimensionality Reduction

Reducing Redundancy in the Bottleneck Representation of the Autoencoders

no code implementations9 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.

Dimensionality Reduction Image Compression +1

Learning to ignore: rethinking attention in CNNs

1 code implementation10 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.

Robust channel-wise illumination estimation

1 code implementation10 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.

Color Constancy

Improving Neural Network Generalization via Promoting Within-Layer Diversity

no code implementations29 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.

Learning distinct features helps, provably

no code implementations10 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.

Generalization Bounds

On Feature Diversity in Energy-based models

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.

Generalization Bounds regression

ON NEURAL NETWORK GENERALIZATION VIA PROMOTING WITHIN-LAYER ACTIVATION DIVERSITY

no code implementations1 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.

Graph Embedding with Data Uncertainty

no code implementations1 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.

Graph Embedding

Probabilistic Color Constancy

no code implementations6 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).

Color Constancy

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

Color Constancy Convolutional Autoencoder

no code implementations4 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.

Color Constancy Unsupervised Pre-training

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