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.

#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)

Public facing deeplift repo

A Simple pytorch implementation of GradCAM and GradCAM++

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

Tensorflow tutorial for various Deep Neural Network visualization techniques

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

[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

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

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

Protein-compound affinity prediction through unified RNN-CNN

Pytorch Implementation of recent visual attribution methods for model interpretability

#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

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

Pytorch implementation of various neural network interpretability methods

#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

All about explainable AI, algorithmic fairness and more

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

#计算机科学#[ICCV 2021] Towards Interpretable Deep Metric Learning with Structural Matching

#计算机科学#Implementation of Layerwise Relevance Propagation for heatmapping "deep" layers