interpretable-deep-learning | Topic

Topic: "interpretable-deep-learning"

jacobgil/pytorch-grad-cam

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Language: Python - Size: 134 MB - Last synced at: about 1 month ago - Pushed at: 3 months ago - Stars: 11,641 - Forks: 1,636

frgfm/torch-cam

Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)

Language: Python - Size: 10.3 MB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 2,192 - Forks: 220

kundajelab/deeplift

Public facing deeplift repo

Language: Python - Size: 10.7 MB - Last synced at: about 1 hour ago - Pushed at: about 3 years ago - Stars: 859 - Forks: 168

MinghuiChen43/awesome-trustworthy-deep-learning

A curated list of trustworthy deep learning papers. Daily updating...

Size: 7.71 MB - Last synced at: 5 days ago - Pushed at: 5 days ago - Stars: 369 - Forks: 37

1202kbs/Understanding-NN

Tensorflow tutorial for various Deep Neural Network visualization techniques

Language: Jupyter Notebook - Size: 6.63 MB - Last synced at: about 2 months ago - Pushed at: almost 5 years ago - Stars: 347 - Forks: 88

1Konny/gradcam_plus_plus-pytorch

A Simple pytorch implementation of GradCAM and GradCAM++

Language: Jupyter Notebook - Size: 10.9 MB - Last synced at: over 1 year ago - Pushed at: about 6 years ago - Stars: 312 - Forks: 87

ShengcaiLiao/QAConv

[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

Language: Python - Size: 5.42 MB - Last synced at: over 1 year ago - Pushed at: over 2 years ago - Stars: 188 - Forks: 30

suinleelab/path_explain

A repository for explaining feature attributions and feature interactions in deep neural networks.

Language: Jupyter Notebook - Size: 204 MB - Last synced at: about 2 months ago - Pushed at: over 3 years ago - Stars: 187 - Forks: 29

hate-alert/HateXplain

Can we use explanations to improve hate speech models? Our paper accepted at AAAI 2021 tries to explore that question.

Language: Python - Size: 6.57 MB - Last synced at: over 1 year ago - Pushed at: about 2 years ago - Stars: 173 - Forks: 62

pietrobarbiero/pytorch_explain

PyTorch Explain: Interpretable Deep Learning in Python.

Language: Jupyter Notebook - Size: 42.1 MB - Last synced at: about 1 month ago - Pushed at: about 1 year ago - Stars: 154 - Forks: 14

Shen-Lab/DeepAffinity

Protein-compound affinity prediction through unified RNN-CNN

Language: Python - Size: 307 MB - Last synced at: about 1 month ago - Pushed at: 11 months ago - Stars: 146 - Forks: 31

yulongwang12/visual-attribution

Pytorch Implementation of recent visual attribution methods for model interpretability

Language: Jupyter Notebook - Size: 27.7 MB - Last synced at: over 1 year ago - Pushed at: over 5 years ago - Stars: 141 - Forks: 25

laura-rieger/deep-explanation-penalization

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

Language: Jupyter Notebook - Size: 248 MB - Last synced at: about 1 month ago - Pushed at: over 4 years ago - Stars: 127 - Forks: 14

suinleelab/attributionpriors

Tools for training explainable models using attribution priors.

Language: Jupyter Notebook - Size: 95.4 MB - Last synced at: 19 days ago - Pushed at: over 4 years ago - Stars: 124 - Forks: 8

andreysharapov/xaience

All about explainable AI, algorithmic fairness and more

Language: HTML - Size: 7.81 GB - Last synced at: about 1 year ago - Pushed at: over 1 year ago - Stars: 106 - Forks: 12

hans66hsu/nn_interpretability

Pytorch implementation of various neural network interpretability methods

Language: Jupyter Notebook - Size: 30.5 MB - Last synced at: about 1 year ago - Pushed at: over 3 years ago - Stars: 104 - Forks: 19

M-Nauta/ProtoTree

ProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image Recognition, published at CVPR2021

Language: Python - Size: 870 KB - Last synced at: about 1 month ago - Pushed at: almost 3 years ago - Stars: 101 - Forks: 21

wl-zhao/DIML

[ICCV 2021] Towards Interpretable Deep Metric Learning with Structural Matching

Language: Python - Size: 1.52 MB - Last synced at: about 1 month ago - Pushed at: almost 4 years ago - Stars: 99 - Forks: 12

inouye-lab/ShapleyExplanationNetworks

Implementation of the paper "Shapley Explanation Networks"

Language: Python - Size: 25.4 KB - Last synced at: almost 2 years ago - Pushed at: over 4 years ago - Stars: 75 - Forks: 18

wjNam/Relative_Attributing_Propagation

Interpreting DNNs, Relative attributing propagation

Language: Python - Size: 3.55 MB - Last synced at: 11 months ago - Pushed at: over 4 years ago - Stars: 75 - Forks: 9

wanyu-lin/ICML2021-Gem

Official code for the ICML 2021 paper "Generative Causal Explanations for Graph Neural Networks."

Language: Jupyter Notebook - Size: 21.4 MB - Last synced at: 7 months ago - Pushed at: about 3 years ago - Stars: 65 - Forks: 9

PKUAI26/AT-CNN

Project page for our paper: Interpreting Adversarially Trained Convolutional Neural Networks

Language: Python - Size: 7.44 MB - Last synced at: over 2 years ago - Pushed at: almost 6 years ago - Stars: 62 - Forks: 9

scottgigante/m-phate

Multislice PHATE for tensor embeddings

Language: Python - Size: 135 MB - Last synced at: 4 days ago - Pushed at: over 4 years ago - Stars: 59 - Forks: 8

ryanchankh/redunet_paper

Official NumPy Implementation of Deep Networks from the Principle of Rate Reduction (2021)

Language: Python - Size: 373 KB - Last synced at: about 1 year ago - Pushed at: about 4 years ago - Stars: 58 - Forks: 8

amirfeder/CausaLM

CausaLM: Causal Model Explanation Through Counterfactual Language Models

Language: Python - Size: 2.5 MB - Last synced at: almost 2 years ago - Pushed at: about 5 years ago - Stars: 46 - Forks: 12

M-Nauta/PIPNet

PIP-Net: Patch-based Intuitive Prototypes Network for Interpretable Image Classification (CVPR 2023)

Language: Python - Size: 3.85 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 43 - Forks: 8

jialinwu17/self_critical_vqa

Code for NeurIPS 2019 paper ``Self-Critical Reasoning for Robust Visual Question Answering''

Language: Python - Size: 74.6 MB - Last synced at: over 2 years ago - Pushed at: almost 6 years ago - Stars: 39 - Forks: 9

ducminhkhoi/InterpretableCNN

Language: Python - Size: 6.84 KB - Last synced at: about 2 years ago - Pushed at: about 7 years ago - Stars: 39 - Forks: 13

matlab-deep-learning/Explore-Deep-Network-Explainability-Using-an-App

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.

Language: MATLAB - Size: 26.3 MB - Last synced at: about 2 months ago - Pushed at: almost 4 years ago - Stars: 36 - Forks: 7

rakhimovv/tcav

Quantitative Testing with Concept Activation Vectors in PyTorch

Language: Python - Size: 19.5 KB - Last synced at: over 2 years ago - Pushed at: over 6 years ago - Stars: 33 - Forks: 14

Jathurshan0330/Cross-Modal-Transformer

Official repository of cross-modal transformer for interpretable automatic sleep stage classification. https://arxiv.org/abs/2208.06991

Language: Jupyter Notebook - Size: 152 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 32 - Forks: 3

nadeemlab/CIR

Clinically-Interpretable Radiomics [MICCAI'22, CMPB'21]

Language: Python - Size: 2.06 MB - Last synced at: 6 months ago - Pushed at: over 2 years ago - Stars: 30 - Forks: 6

williamcaicedo/ISeeU

ISeeU: Visually interpretable deep learning for mortality prediction inside the ICU

Language: Jupyter Notebook - Size: 13.1 MB - Last synced at: 29 days ago - Pushed at: over 4 years ago - Stars: 28 - Forks: 7

QData/AttentiveChrome

NeurIPS17: [AttentiveChrome] Attend and Predict: Using Deep Attention Model to Understand Gene Regulation by Selective Attention on Chromatin

Language: Lua - Size: 78.1 MB - Last synced at: about 2 months ago - Pushed at: over 4 years ago - Stars: 27 - Forks: 9

seilna/CNN-Units-in-NLP

:scissors: Repository for our ICLR 2019 paper: Discovery of Natural Language Concepts in Individual Units of CNNs

Language: Python - Size: 3.43 MB - Last synced at: over 2 years ago - Pushed at: over 6 years ago - Stars: 26 - Forks: 1

epfml/interpret-lm-knowledge

Extracting knowledge graphs from language models as a diagnostic benchmark of model performance (NeurIPS XAI 2021).

Language: Jupyter Notebook - Size: 53.7 KB - Last synced at: about 2 months ago - Pushed at: about 3 years ago - Stars: 25 - Forks: 4

Henrymachiyu/ProtoViT

This code implements ProtoViT, a novel approach that combines Vision Transformers with prototype-based learning to create interpretable image classification models. Our implementation provides both high accuracy and explainability through learned prototypes.

Language: Python - Size: 1020 KB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 22 - Forks: 7

priyamtejaswin/devise-keras

Interpretable Image Search by Priyam Tejaswin and Akshay Chawla

Language: Python - Size: 1.84 MB - Last synced at: about 1 year ago - Pushed at: over 2 years ago - Stars: 22 - Forks: 9

JonathanCrabbe/Label-Free-XAI

This repository contains the implementation of Label-Free XAI, a new framework to adapt explanation methods to unsupervised models. For more details, please read our ICML 2022 paper: 'Label-Free Explainability for Unsupervised Models'.

Language: Python - Size: 8.19 MB - Last synced at: about 1 year ago - Pushed at: over 2 years ago - Stars: 22 - Forks: 9

iurada/px-ntk-pruning

Official repository of our work "Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning" accepted at CVPR 2024

Language: Python - Size: 699 KB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 21 - Forks: 4

mims-harvard/TimeX

Time series explainability via self-supervised model behavior consistency

Language: Python - Size: 29 MB - Last synced at: about 1 year ago - Pushed at: over 1 year ago - Stars: 21 - Forks: 1

cwangrun/ST-ProtoPNet

[ICCV 2023] Learning Support and Trivial Prototypes for Interpretable Image Classification

Language: Python - Size: 841 KB - Last synced at: 7 months ago - Pushed at: 7 months ago - Stars: 20 - Forks: 2

kundajelab/fastISM

In-silico Saturation Mutagenesis implementation with 10x or more speedup for certain architectures.

Language: Jupyter Notebook - Size: 5.94 MB - Last synced at: about 1 month ago - Pushed at: about 3 years ago - Stars: 20 - Forks: 3

benjaminpatrickevans/XAI

Genetic programming method for explaining complex black-box models

Language: Python - Size: 73.2 KB - Last synced at: 7 days ago - Pushed at: about 1 year ago - Stars: 19 - Forks: 3

Z80coder/db-nets

∂B nets: learning discrete, boolean-valued functions by gradient descent

Language: Mathematica - Size: 55.3 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 18 - Forks: 3

Js-Mim/rl_singing_voice

Unsupervised Representation Learning for Singing Voice Separation

Language: Python - Size: 21.5 MB - Last synced at: over 2 years ago - Pushed at: over 2 years ago - Stars: 18 - Forks: 4

heartcored98/transformer_anatomy

Official Pytorch implementation of (Roles and Utilization of Attention Heads in Transformer-based Neural Language Models), ACL 2020

Language: Python - Size: 30.8 MB - Last synced at: 2 months ago - Pushed at: 3 months ago - Stars: 16 - Forks: 4

shinkyo0513/Towards-Visually-Explaining-Video-Understanding-Networks-With-Perturbation

Attribution (or visual explanation) methods for understanding video classification networks. Demo codes for WACV2021 paper: Towards Visually Explaining Video Understanding Networks with Perturbation.

Language: Python - Size: 166 MB - Last synced at: over 2 years ago - Pushed at: over 2 years ago - Stars: 15 - Forks: 0

1Konny/class_selectivity_index

On the importance of single directions for generalization(Morcos et al, ICLR 2018)

Language: Shell - Size: 1.51 MB - Last synced at: over 2 years ago - Pushed at: almost 7 years ago - Stars: 15 - Forks: 2

PrashantSaikia/Dynamic-SHAP-Plots

Enabling interactive plotting of the visualizations from the SHAP project.

Language: Python - Size: 40 KB - Last synced at: about 2 years ago - Pushed at: over 5 years ago - Stars: 14 - Forks: 3

pnxenopoulos/cav-keras

Concept activation vectors for Keras

Language: Python - Size: 23 MB - Last synced at: over 2 years ago - Pushed at: over 2 years ago - Stars: 13 - Forks: 6

ShengcaiLiao/TransMatcher

[NeurIPS 2021] TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification

Language: Python - Size: 5.28 MB - Last synced at: over 2 years ago - Pushed at: almost 3 years ago - Stars: 13 - Forks: 2

ajsanjoaquin/Shapley_Valuation

PyTorch reimplementation of computing Shapley values via Truncated Monte Carlo sampling from "What is your data worth? Equitable Valuation of Data" by Amirata Ghorbani and James Zou [ICML 2019]

Language: Python - Size: 34.2 KB - Last synced at: over 2 years ago - Pushed at: over 3 years ago - Stars: 13 - Forks: 3

Trustworthy-ML-Lab/CB-LLMs

[ICLR 25] A novel framework for building intrinsically interpretable LLMs with human-understandable concepts to ensure safety, reliability, transparency, and trustworthiness.

Language: Python - Size: 936 KB - Last synced at: 26 days ago - Pushed at: 26 days ago - Stars: 12 - Forks: 3

prclibo/ice

Interpretable Control Exploration and Counterfactual Explanation (ICE) on StyleGAN

Language: Jupyter Notebook - Size: 8.43 MB - Last synced at: about 2 years ago - Pushed at: over 3 years ago - Stars: 12 - Forks: 6

ilyalasy/moe-routing

Analysis of token routing for different implementations of Mixture of Experts

Language: Jupyter Notebook - Size: 882 KB - Last synced at: 3 months ago - Pushed at: over 1 year ago - Stars: 9 - Forks: 0

sauravmishra1710/Malaria-Detection-Using-Deep-Learning-Techniques

Malaria Parasite Detection using Efficient Neural Ensembles. Malaria, a life threatening disease caused by the bite of the Anopheles mosquito infected with the parasite, has been a major burden towards healthcare for years leading to approximately 400,000 deaths globally every year. This study aims to build an efficient system by applying ensemble techniques based on deep learning to automate the detection of the parasite using whole slide images of thin blood smears.

Language: Jupyter Notebook - Size: 295 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 9 - Forks: 5

sandareka/Interpretability-of-Machine-Learning-Visualizations

Interpretability of Machine Learning-Visualizations

Language: Python - Size: 1.1 MB - Last synced at: almost 2 years ago - Pushed at: almost 7 years ago - Stars: 9 - Forks: 2

sandareka/CCNN

Comprehensible Convolutional Neural Networks via Guided Concept Learning

Language: Python - Size: 2.76 MB - Last synced at: almost 2 years ago - Pushed at: almost 3 years ago - Stars: 8 - Forks: 2

Trustworthy-ML-Lab/posthoc-generative-cbm

[CVPR 2025] Concept Bottleneck Autoencoder (CB-AE) -- efficiently transform any pretrained (black-box) image generative model into an interpretable generative concept bottleneck model (CBM) with minimal concept supervision, while preserving image quality

Language: Jupyter Notebook - Size: 3 MB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 7 - Forks: 1

mmmmayi/ExPO

official implementation of paper ExPO: Explainable Phonetic Trait-Oriented Network for Speaker Verification

Language: Python - Size: 113 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 7 - Forks: 0

nphdang/DeepCoDA

Deep learning for personalized interpretability for compositional health data

Language: Python - Size: 10.8 MB - Last synced at: almost 2 years ago - Pushed at: about 3 years ago - Stars: 6 - Forks: 1

AIMedLab/ecg-diagnosis

Code and Datasets for the paper "Interpretable deep learning for automatic diagnosis of 12-lead electrocardiogram", published on iScience in 2021.

Language: Python - Size: 22.5 KB - Last synced at: about 2 years ago - Pushed at: over 4 years ago - Stars: 6 - Forks: 1

shinkyo0513/Surgical-Skill-Assessment-via-Video-Semantic-Aggregation

Code for Surgical Skill Assessment via Video Semantic Aggregation (MICCAI 2022)

Language: Python - Size: 3.41 MB - Last synced at: over 2 years ago - Pushed at: over 2 years ago - Stars: 5 - Forks: 0

jnikhilreddy/Explainable-AI-papers-Year-wise

List of papers in the area of Explainable Artificial Intelligence Year wise

Size: 18.6 KB - Last synced at: over 2 years ago - Pushed at: over 5 years ago - Stars: 5 - Forks: 1

gudovskiy/e2x

Explain to Fix: A Framework to Interpret and Correct DNN Object Detector Predictions

Language: C++ - Size: 110 KB - Last synced at: over 2 years ago - Pushed at: over 6 years ago - Stars: 5 - Forks: 0

DrejcPesjak/scaling-monosemanticity-llama

Reproducing Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet using LLaMA. This project explores monosemantic neurons in large language models, implementing and extending methods to scale and analyze interpretability in LLaMA-based architectures.

Language: Jupyter Notebook - Size: 14.7 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 4 - Forks: 0

david-gimeno/interpreting-ssl-parkinson-speech

Official source code of the paper: "Unveiling Interpretability in Self-Supervised Speech Representations for Parkinson’s Diagnosis"

Language: Jupyter Notebook - Size: 3.78 MB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 4 - Forks: 1

mateoespinosa/tabcbm

Official Implementation of TMLR's paper: "TabCBM: Concept-based Interpretable Neural Networks for Tabular Data"

Language: Python - Size: 11.8 MB - Last synced at: 11 months ago - Pushed at: about 1 year ago - Stars: 4 - Forks: 2

machinelearningnuremberg/INN

Explainable deep networks that are not only as accurate as their black-box deep-learning counterparts but also as interpretable as state-of-the-art explanation techniques.

Language: Python - Size: 60.5 KB - Last synced at: 11 months ago - Pushed at: over 1 year ago - Stars: 4 - Forks: 0

aywi/mprotonet

MProtoNet: A Case-Based Interpretable Model for Brain Tumor Classification with 3D Multi-parametric Magnetic Resonance Imaging

Language: Python - Size: 184 KB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 4 - Forks: 0

manuelbre/Reliable-and-Interpretable-AI-HS18

Assignments and projects for the ETH Zurich Reliable and Interpretable Artificial Intelligence class autumn 2018

Language: Jupyter Notebook - Size: 13.4 MB - Last synced at: over 2 years ago - Pushed at: over 2 years ago - Stars: 4 - Forks: 1

AFAgarap/dnn-trust

How can I trust you? An intuition and tutorial on trust score

Language: Jupyter Notebook - Size: 41 MB - Last synced at: over 2 years ago - Pushed at: over 2 years ago - Stars: 4 - Forks: 2

ajsanjoaquin/mPerturb

Implementation of Interpretable Explanations of Black Boxes by Meaningful Perturbation (Fong, et. al., 2018)

Language: Jupyter Notebook - Size: 2.52 MB - Last synced at: over 2 years ago - Pushed at: about 3 years ago - Stars: 4 - Forks: 1

AIMedLab/TransICD

Code and Datasets for the paper "TransICD: Transformer Based Code-wise Attention Model for Explainable ICD Coding", accepted by AIME 2021.

Language: Python - Size: 1.52 MB - Last synced at: over 2 years ago - Pushed at: about 4 years ago - Stars: 4 - Forks: 1

EloiZ/awesome-contrastive-explanation

A curated list of awesome contrastive explanation in ML resources

Size: 18.6 KB - Last synced at: 9 days ago - Pushed at: over 5 years ago - Stars: 4 - Forks: 0

1pha/brain-age-prediction

Brain age prediction and networks explainability on their decision

Language: Jupyter Notebook - Size: 828 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 3 - Forks: 0

sentspace/sentspace Fork of aalok-sathe/sentspace

a module to obtain diverse real-world-grounded features for sentences for large-scale benchmarking

Language: Python - Size: 835 KB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 3 - Forks: 1