interpretable-deep-learning

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

深度学习 PyTorch grad-cam visualizations interpretability interpretable-ai interpretable-deep-learning score-cam class-activation-maps vision-transformers explainable-ai xai image-classification 机器学习 object-detection 机器视觉 explainable-ml

Python 11.99 k

4 个月前

frgfm / torch-cam

#计算机科学#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)

PyTorch Python 深度学习 cnn gradcam saliency-map interpretability interpretable-deep-learning score-cam grad-cam

Python 2.23 k

2 天前

kundajelab / deeplift

Public facing deeplift repo

guided-backpropagation saliency-map interpretable-deep-learning interpretability

Python 861

3 年前

1Konny / gradcam_plus_plus-pytorch

A Simple pytorch implementation of GradCAM and GradCAM++

gradcam interpretable-deep-learning

Jupyter Notebook 384

6 年前

MinghuiChen43 / awesome-trustworthy-deep-learning

#计算机科学#A curated list of trustworthy deep learning papers. Daily updating...

adversarial-machine-learning 安全隐私深度学习 poisoning fairness backdoor ownership robustness interpretable-deep-learning causality hallucinations uncertainty watermarking ai-alignment

371

9 天前

1202kbs / Understanding-NN

Tensorflow tutorial for various Deep Neural Network visualization techniques

Tensorflow 机器视觉教程 interpretable-deep-learning

Jupyter Notebook 346

5 年前

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

person-reidentification person-reid re-identification interpretability interpretable-deep-learning correspondence image-matching generalization deep-metric-learning metric-learning reid domain-generalization

Python 212

3 年前

hate-alert / HateXplain

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

explainability bias offensive detection interpretable-deep-learning bert-model lstm

Python 210

2 年前

suinleelab / path_explain

#计算机科学#A repository for explaining feature attributions and feature interactions in deep neural networks.

机器学习 interpretable-deep-learning explainable-ai Tensorflow PyTorch

Jupyter Notebook 188

4 年前

pietrobarbiero / pytorch_explain

#计算机科学#PyTorch Explain: Interpretable Deep Learning in Python.

logic PyTorch Python 机器学习神经网络深度学习 explainability explainable-ai lens entropy sympy interpretability interpretable-ai interpretable-deep-learning interpretable-machine-learning

Jupyter Notebook 159

1 年前

Shen-Lab / DeepAffinity

Protein-compound affinity prediction through unified RNN-CNN

drug-discovery interpretable-deep-learning semi-supervised-learning attention-mechanism protein

Python 147

1 年前

yulongwang12 / visual-attribution

Pytorch Implementation of recent visual attribution methods for model interpretability

PyTorch saliency interpretability model-interpretability xai interpretable-deep-learning

Jupyter Notebook 146

5 年前

laura-rieger / deep-explanation-penalization

#计算机科学#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

interpretability 神经网络机器学习 convolutional-neural-network PyTorch explainability 深度学习 explainable-ai 人工智能 Python 数据科学 Jupyter Notebook feature-importance recurrent-neural-network fairness fairness-ml interpretable-deep-learning

Jupyter Notebook 128

4 年前

suinleelab / attributionpriors

#计算机科学#Tools for training explainable models using attribution priors.

机器学习 interpretable-deep-learning Tensorflow 人工智能

Jupyter Notebook 124

4 年前

hans66hsu / nn_interpretability

Pytorch implementation of various neural network interpretability methods

PyTorch interpretable-deep-learning saliency-map guided-backpropagation gradcam gradient-visualization

Jupyter Notebook 118

3 年前

andreysharapov / xaience

All about explainable AI, algorithmic fairness and more

explainable-ai explainable-ml interpretable-machine-learning interpretable-ai interpretable-deep-learning interpretability

HTML 110

2 年前

Trustworthy-ML-Lab / Label-free-CBM

#计算机科学#[ICLR 23] A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled concept data

机器视觉深度学习深度神经网络 interpretability interpretable-deep-learning

Jupyter Notebook 108

1 年前