Global-Local Capsule Network (GLCapsNet) is a capsule-based architecture able to provide context-based eye fixation prediction for several autonomous driving scenarios, while offering interpretability both globally and locally.

✭ 33

python shell Dockerfile computer-vision deep-learning convolutional-neural-networks autonomous-driving autonomous-vehicles interpretability capsule-networks visual-attention context-specific

Transformer-MM-Explainability

[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.

✭ 484

Jupyter Notebook python javascript shell c CSS visualization transformers transformer vqa clip interpretability explainable-ai explainability detr lxmert visualbert

adversarial-robustness-public

Code for AAAI 2018 accepted paper: "Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients"

✭ 49

Jupyter Notebook python interpretability robustness

ArenaR

Data generator for Arena - interactive XAI dashboard

✭ 28

r ema interpretability xai iml explainability explanatory-model-analysis axplainable-artificial-intelligence interactive-xai

EgoCNN

Code for "Distributed, Egocentric Representations of Graphs for Detecting Critical Structures" (ICML 2019)

✭ 16

python Jupyter Notebook shell convolutional-neural-networks self-similarity interpretability icml graph-embeddings scale-free-networks graph-neural-networks graph-networks graph-convolutional-neural-networks icml-2019

concept-based-xai

Library implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI

✭ 41

python shell library weak-supervision vae concept concept-extraction weakly-supervised-learning interpretability disentanglement model-explanation explainable-ai disentangled-representations xai explainability concept-explanation

xai-iml-sota

Interesting resources related to Explainable Artificial Intelligence, Interpretable Machine Learning, Interactive Machine Learning, Human in Loop and Visual Analytics.

ALPS 2021

XAI Tutorial for the Explainable AI track in the ALPS winter school 2021

✭ 55

Jupyter Notebook python pytorch colab exercises interpretability colab-notebook explainability captum

kernel-mod

NeurIPS 2018. Linear-time model comparison tests.

✭ 17

Jupyter Notebook python shell machine-learning kernel-methods hypothesis-testing interpretability model-comparison

adaptive-wavelets

Adaptive, interpretable wavelets across domains (NeurIPS 2021)

✭ 58

Jupyter Notebook python machine-learning statistics deep-learning neural-network pytorch interpretability wavelets wavelet-analysis distillation xai explainability

thermostat

Collection of NLP model explanations and accompanying analysis tools

✭ 126

Jsonnet python Jupyter Notebook natural-language-processing transformers datasets heatmaps interpretability explainability saliency-maps feature-attribution captum explainable-nlp

61-80 of 80 interpretability projects

‹