Explainable AI: current status and future directions

TLDR

Explainable AI (XAI) is an emerging field that enables interpretation of AI decisions and is essential for trust in critical domains such as defense, healthcare, law, and autonomous vehicles. The paper aims to provide an overview of XAI techniques across multimedia modalities. It reviews these techniques from a multimedia perspective, covering text, image, audio, and video. The review discusses the advantages and shortcomings of XAI techniques and suggests future research directions.

Abstract

Explainable Artificial Intelligence (XAI) is an emerging area of research in the field of Artificial Intelligence (AI). XAI can explain how AI obtained a particular solution (e.g., classification or object detection) and can also answer other "wh" questions. This explainability is not possible in traditional AI. Explainability is essential for critical applications, such as defense, health care, law and order, and autonomous driving vehicles, etc, where the know-how is required for trust and transparency. A number of XAI techniques so far have been purposed for such applications. This paper provides an overview of these techniques from a multimedia (i.e., text, image, audio, and video) point of view. The advantages and shortcomings of these techniques have been discussed, and pointers to some future directions have also been provided.