aimh-lab Goto Github PK

adversarial-magnification-to-deceive-deepfake-detection-through-super-resolution

Official code for the paper "Adversarial Magnification to Deceive Deepfake Detection through Super Resolution"

cbigan-anomaly-detection

Code to reproduce 'Combining GANs and AutoEncodersfor efficient anomaly detection'

combining-efficientnet-and-vision-transformers-for-video-deepfake-detection

Code for Video Deepfake Detection model from "Combining EfficientNet and Vision Transformers for Video Deepfake Detection" presented at ICIAP 2021.

cross-forgery-analysis-of-vision-transformers-and-cnns-for-deepfake-image-detection

Code for the paper Cross Forgery Analysis of Vision Transformers and CNNs for Deepfake Image Detection

deep-parking

Code to reproduce 'Deep Learning for Decentralized Parking Lot Occupancy Detection' paper.

detecting-images-generated-by-diffusers

gan-universe

This repository contains part of the code used to make the images visible in the article "How does an AI Imagine the Universe?" published on Towards Data Science.

hebbian-learning-cnn

Pytorch implementation of Hebbian learning algorithms to train deep convolutional neural networks.

learning-relationship-aware-visual-features

Relational Content-Based Image Retrieval (R-CBIR) - Retrieving images with given relationships among objects

mafer-multires-facial-expression-recognition

A novel Multi-Resolution approach to solve the Facial Expression Recognition task.

mintime-multi-identity-size-invariant-timesformer-for-video-deepfake-detection

Code for Video Deepfake Detector from "MINTIME: Multi-Identity Size-Invariant Video Deepfake Detection", pre-print available on Arxiv

mocca-anomaly-detection

Code to reproduce 'MOCCA: Multi-Layer One-Class Classification for Anomaly Detection'

neural-ode-features

Pytorch code to train image classifiers based on ODE Nets on MNIST and CIFAR-10, extract features and test robustness to adversarial examples

trj-based-adversarials-detection

Detect adversarial attacks based on features trajectory for Face Recognition and toy datasets

visione

An AI-powered interactive video retrieval system