Omiros Pantazis's repositories
svl_adapter
SVL-Adapter: Self-Supervised Adapter for Vision-Language Pretrained Models
camera_traps_self_supervised
This repository contains the code for reproducing the results of our ICCV 2021 paper: "Focus on the Positives: Self-Supervised Learning for Biodiversity Monitoring".
face-expression-recognition-system
The model was trained with a dataset of approximately 40000 images from the Kaggle Facial Expression Recognition Competition https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge/data
ucl-msc-project
The code in this repository corresponds to part of my MSc project for the MSc in Machine Learning at UCL with title: "Psychophysics for Interpretation of Convolutional Neural Networks and Localization"
CameraTraps
Tools for training and running detectors and classifiers for wildlife images collected from motion-triggered cameras.
CoOp
Prompt Learning for Vision-Language Models (IJCV'22, CVPR'22)
cypher-python
Python functions embedding Cypher queries (Query language for neo4j database) with the use of py2neo library regarding data fetched from Twitter.
twitter-data-collection
Fetch data from Twitter using twitter APIs via tweePy library for python. The data are stored in a neo4j graph database via py2neo library.
geo_prior
Presence-Only Geographical Priors for Fine-Grained Image Classification - ICCV 2019
IIC-fork
Invariant Information Clustering for Unsupervised Image Classification and Segmentation
inat_comp_2018
CNN training code for iNaturalist 2018 image classification competition
LDAM-DRW
[NeurIPS 2019] Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
moco-fork
PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722
ntua_e-prescription
Project for Analysis and Design of Information Systems. It deals with e-prescription.
omipan.github.io
Personal website
statistical-functions
Typical set of statistical functions.
TensorFlow-Examples
TensorFlow Tutorial and Examples for beginners
ucl-irdm-2017
This project is for UCL's course Information Retrieval and Data Mining and is based on Kaggle's Competition 'Home Depot Kaggle Challenge. It includes implementation of Machine Learning models that rank products sold by Home Depot with respect to their relevance to user queries in order to improve the customer's shopping experience.
Unsupervised-Classification-Fork
SCAN: Learning to Classify Images without Labels (ECCV 2020)