path explainA repository for explaining feature attributions and feature interactions in deep neural networks.
Stars: ✭ 151 (+319.44%)
Mutual labels: interpretable-deep-learning
ProtoTreeProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image Recognition, published at CVPR2021
Stars: ✭ 47 (+30.56%)
Mutual labels: interpretable-deep-learning
ShapleyExplanationNetworksImplementation of the paper "Shapley Explanation Networks"
Stars: ✭ 62 (+72.22%)
Mutual labels: interpretable-deep-learning
rl singing voiceUnsupervised Representation Learning for Singing Voice Separation
Stars: ✭ 18 (-50%)
Mutual labels: interpretable-deep-learning
ISeeUISeeU: Visually interpretable deep learning for mortality prediction inside the ICU
Stars: ✭ 20 (-44.44%)
Mutual labels: interpretable-deep-learning
deep-explanation-penalizationCode for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" https://arxiv.org/abs/1909.13584
Stars: ✭ 110 (+205.56%)
Mutual labels: interpretable-deep-learning
m-phateMultislice PHATE for tensor embeddings
Stars: ✭ 54 (+50%)
Mutual labels: interpretable-deep-learning
redunet paperOfficial NumPy Implementation of Deep Networks from the Principle of Rate Reduction (2021)
Stars: ✭ 49 (+36.11%)
Mutual labels: interpretable-deep-learning
self critical vqaCode for NeurIPS 2019 paper ``Self-Critical Reasoning for Robust Visual Question Answering''
Stars: ✭ 39 (+8.33%)
Mutual labels: interpretable-deep-learning
Pytorch Grad CamMany Class Activation Map methods implemented in Pytorch for CNNs and Vision Transformers. Including Grad-CAM, Grad-CAM++, Score-CAM, Ablation-CAM and XGrad-CAM
Stars: ✭ 3,814 (+10494.44%)
Mutual labels: interpretable-deep-learning
Layerwise-Relevance-PropagationImplementation of Layerwise Relevance Propagation for heatmapping "deep" layers
Stars: ✭ 78 (+116.67%)
Mutual labels: interpretable-deep-learning
CNN-Units-in-NLP✂️ Repository for our ICLR 2019 paper: Discovery of Natural Language Concepts in Individual Units of CNNs
Stars: ✭ 26 (-27.78%)
Mutual labels: interpretable-deep-learning