Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
-
Updated
Apr 7, 2025 - Python
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
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
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
Protein-compound affinity prediction through unified RNN-CNN
ProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image Recognition, published at CVPR2021
[ICCV 2021] Towards Interpretable Deep Metric Learning with Structural Matching
Implementation of Layerwise Relevance Propagation for heatmapping "deep" layers
Implementation of the paper "Shapley Explanation Networks"
Interpreting DNNs, Relative attributing propagation
PIP-Net: Patch-based Intuitive Prototypes Network for Interpretable Image Classification (CVPR 2023)
Project page for our paper: Interpreting Adversarially Trained Convolutional Neural Networks
Multislice PHATE for tensor embeddings
Official NumPy Implementation of Deep Networks from the Principle of Rate Reduction (2021)
CausaLM: Causal Model Explanation Through Counterfactual Language Models
Time series explainability via self-supervised model behavior consistency
Quantitative Testing with Concept Activation Vectors in PyTorch
Code for NeurIPS 2019 paper ``Self-Critical Reasoning for Robust Visual Question Answering''
Add a description, image, and links to the interpretable-deep-learning topic page so that developers can more easily learn about it.
To associate your repository with the interpretable-deep-learning topic, visit your repo's landing page and select "manage topics."