Lennart Brocki's repositories
concept-saliency-maps
Contains the jupyter notebooks to reproduce the results of the paper "Concept Saliency Maps to Visualize Relevant Features in Deep Generative Models" https://arxiv.org/pdf/1910.13140.pdf
NoBias-Rectified-Gradient
We introduce a modification of Rectified Gradient. This repository is forked from https://github.com/1202kbs/Rectified-Gradient
Feature-Perturbation-Augmentation
This repository contains the code to reproduce the results of our paper Feature Perturbation Augmentation (FPA)
Conditional_Diffusion_LIDC
Conditional diffusion model to generate LIDC. Minimal script. Based on 'Classifier-Free Diffusion Guidance'.
DeepExplain
A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also includes support for Shapley Values sampling. (ICLR 2018)
dino
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
gitignore
A collection of useful .gitignore templates
saliency
Framework-agnostic implementation for state-of-the-art saliency methods (XRAI, BlurIG, SmoothGrad, and more).
SliceViewer
Simple Jupyter widget for viewing slices of 3D images
Transformer-MM-Explainability
[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.