Welcome to xaitk-saliency’s documentation!

Welcome to the documentation for XAITK-Saliency. As part of the Explainable AI Toolkit (XAITK), XAITK-Saliency is an open source, explainable AI framework for visual saliency algorithm interfaces and implementations, built for analytics and autonomy applications. The xaitk-saliency package provides saliency algorithms for a wide range of image understanding tasks, including image classification, image similarity, object detection, and reinforcement learning. The current list of supported saliency algorithms can be found in Saliency Algorithms.

This documentation is structured to provide you with straightforward and practical instructions and examples, so that you can effectively leverage the toolkit to enhance the robustness and reliability of your computer vision applications in facing real-world challenges.

Documentation Contents:

Quick Start

• Installation

Tutorials

• Tutorial: Using Occlusion-based Saliency to Explain Image Classification Models
• Tutorial: Using DRISE to Explain Object Detection Models

Explanation

• Introduction
• Design Decisions
• Frequently Asked Questions

How-To

• Review Process
• Steps of the xaitk-saliency Release Process

Reference

• Interfaces
• Implementations
• Release Notes

Indices and tables

• Index

• Module Index

• Search Page