vidhyakamakshi/xai

Papers and code of Explainable AI esp. w.r.t. Image classificiation

XAI

Papers and code of Explainable AI esp. w.r.t. Image classificiation

2013 Conference Papers

Title	Paper Title	Source Link	Code	Tags
Visualization of CNN	Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps	CVPR2013	PyTorch	Visualization gradient-based saliency maps

2016 Conference Papers

Title	Paper Title	Source Link	Code	Tags
CAM	Learning Deep Features for Discriminative Localization	CVPR2016	PyTorch (Official)	class activation mapping
LIME	“Why Should I Trust You?”Explaining the Predictions of Any Classifier	KDD2016	PyTorch (Official)	trust a prediction

2017 Conference Papers

Title	Paper Title	Source Link	Code	Tags
Grad-CAM	Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization	ICCV2017, CVPR2016 (original)	PyTorch	Visualization gradient-based saliency maps
Network Dissection	Network Dissection: Quantifying Interpretability of Deep Visual Representations	CVPR2017	PyTorch (Official)	Visualization

2018 Conference Papers

Title	Paper Title	Source Link	Code	Tags
TCAV	Interpretability Beyond Feature Attribution:Quantitative Testing with Concept Activation Vectors (TCAV)	ICML2018	Tensorflow	interpretability method
Interpretable CNN	Interpretable Convolutional Neural Networks	CVPR2018	Tensorflow	explainability by design

2019 Conference Papers

Title	Paper Title	Source Link	Code	Tags
Full-grad	Full-Gradient Representation for Neural Network Visualization	NeurIPS2019	PyTorch (Official) Tensorflow	saliency map representation
This looks like that	This Looks Like That: Deep Learning for Interpretable Image Recognition	NIPS2019	PyTorch (Official)	object

2020 Papers

Title	Paper Title	Source Link	Code	Tags
INN	Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNs	ECCV 2020 Project Page	PyTorch	explainability by design
X-Grad CAM	Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs		PyTorch