Generation of 3D/ 2D attention maps for both classification and segmentation

Codes for paper: Automatic Knee Osteoarthritis Diagnosis from Plain Radiographs: A Deep Learning-Based Approach

This is the PyTorch implementation of Double Attention Network, NIPS 2018

GEBI: Global Explanations for Bias Identification. Open source code for discovering bias in data with skin lesion dataset

Interactive tool built on top of CLIP for classifying full images or cropped tiles.

A solid foundational understanding of XAI, primarily emphasizing how XAI methodologies can expose latent biases in datasets and reveal valuable insights.

An Interpretable Swin Tranformer Arquitecture for Image Steganalysis in Spatial Domine

An interactive lab for analyzing Vision Transformer robustness through real-time attention map visualization and adversarial attack simulations.

This repository contains the main code and data associated with the article "The geometry of BERT" by Matteo Bonino, Giorgia Ghione, and Giansalvo Cirrincione.

Vision Transformer (ViT-B/16) for deepfake detection on FaceForensics++ C23, with robustness evaluation and attention map visualization.

Methodology used to classify face images based on unknown criteria as part of a datachallenge organised at Telecom Paris

CSE 256 LIGN 256 - Statistical Natural Lang Proc - Nakashole [FA24] PA2

Cross-platform desktop app for lung cancer risk prediction from low-dose CT scans, powered by the Sybil v1.6.0 deep learning model. DICOM/PNG input, 6-year risk scores, attention maps, audit toolkit.