There are 34 repositories under interpretable-deep-learning topic.
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
Public facing deeplift repo
Tensorflow tutorial for various Deep Neural Network visualization techniques
A Simple pytorch implementation of GradCAM and GradCAM++
A curated list of trustworthy deep learning papers. Daily updating...
[ECCV 2020] QAConv: Interpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting, and [CVPR 2022] GS: Graph Sampling Based Deep Metric Learning
A repository for explaining feature attributions and feature interactions in deep neural networks.
Can we use explanations to improve hate speech models? Our paper accepted at AAAI 2021 tries to explore that question.
Pytorch Implementation of recent visual attribution methods for model interpretability
Protein-compound affinity prediction through unified RNN-CNN
PyTorch Explain: Interpretable Deep Learning in Python.
Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" https://arxiv.org/abs/1909.13584
Tools for training explainable models using attribution priors.
All about explainable AI, algorithmic fairness and more
Pytorch implementation of various neural network interpretability methods
Implementation of Layerwise Relevance Propagation for heatmapping "deep" layers
Implementation of the paper "Shapley Explanation Networks"
Interpreting DNNs, Relative attributing propagation
Multislice PHATE for tensor embeddings
Official code for the ICML 2021 paper "Generative Causal Explanations for Graph Neural Networks."
Official NumPy Implementation of Deep Networks from the Principle of Rate Reduction (2021)
Code for NeurIPS 2019 paper ``Self-Critical Reasoning for Robust Visual Question Answering''
Official repository of cross-modal transformer for interpretable automatic sleep stage classification. https://arxiv.org/abs/2208.06991
This repository provides an app for exploring the predictions of an image classification network using several deep learning visualization techniques. Using the app, you can: explore network predictions with occlusion sensitivity, Grad-CAM, and gradient attribution methods, investigate misclassifications using confusion and t-SNE plots, visualize layer activations, and many more techniques to help you understand and explain your deep network’s predictions.
NeurIPS17: [AttentiveChrome] Attend and Predict: Using Deep Attention Model to Understand Gene Regulation by Selective Attention on Chromatin
:scissors: Repository for our ICLR 2019 paper: Discovery of Natural Language Concepts in Individual Units of CNNs
ISeeU: Visually interpretable deep learning for mortality prediction inside the ICU
[NeurIPS 2021] TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification