Luigi Celona's repositories
models-comparison.pytorch
Code for the paper Benchmark Analysis of Representative Deep Neural Network Architectures
spectral-similarity-metrics-comparison
Code for the paper An analysis of spectral similarity measures
BIQA4ConsumerPhotographs
Source code for the paper "Blind Image Quality Assessment of Authentically Distorted Images"
al-folio
A beautiful, simple, clean, and responsive Jekyll theme for academics
arid.github.io
Why DeepDive 🌊 Because the format is liquid 💦 😉
EmailClient
Email Client for reading and sending emails.
examples
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
Exposure_Correction
Reference code for the paper "Learning to Correct Overexposed and Underexposed Photos". Our method is a coarse-to-fine deep learning model to correct badly-exposed photographs.
FoHIS
Towards Simulating Foggy and Hazy Images and Evaluating their Authenticity
google-research
Google Research
Grid-Anchor-based-Image-Cropping-Pytorch
PyTorch implementation of "Grid anchor based image cropping"
jax-CycleGAN-and-pix2pix
Image-to-Image Translation in PyTorch
mthesis-denoise
Master thesis on image denoising with the Natural Image Noise Dataset, convolutional neural networks, and generative adverserial networks.
PracticalSessions2020
Repository for tutorial sessions at EEML2020
PseudoLabeling
Official implementation of "Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning"
pyannote-audio
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
pyannote-database
Reproducible experimental protocols for multimedia (audio, video, text) database
python-scopus
PyScopus
PyTorch-EMDLoss
PyTorch 1.0 implementation of the approximate Earth Mover's Distance
SERAB
SERAB: a multi-lingual benchmark for speech emotion recognition
tutorials2021
Mediterranean Machine Learning school tutorials
tutorials2022
The M2L school 2022 tutorials
unified-embedding
Code and instruction on replicating the experiments done in paper: Unified Hypersphere Embedding for Speaker Recognition
voxceleb_trainer
In defence of metric learning for speaker recognition
voxsrc_2019
VoxSRC Challenge