Visual explanation of black-box model: Similarity Difference and Uniqueness (SIDU) method
This addresses the need for human-understandable explanations in AI for users and developers, though it appears incremental as it builds on existing XAI frameworks.
The paper tackles the problem of explaining black-box AI models by introducing the SIDU method, a visual explanation algorithm that localizes object regions for prediction, and demonstrates its superior performance through multiple evaluations including adversarial attack tests.
Explainable Artificial Intelligence (XAI) has in recent years become a well-suited framework to generate human understandable explanations of "black-box" models. In this paper, a novel XAI visual explanation algorithm known as the Similarity Difference and Uniqueness (SIDU) method that can effectively localize entire object regions responsible for prediction is presented in full detail. The SIDU algorithm robustness and effectiveness is analyzed through various computational and human subject experiments. In particular, the SIDU algorithm is assessed using three different types of evaluations (Application, Human and Functionally-Grounded) to demonstrate its superior performance. The robustness of SIDU is further studied in the presence of adversarial attack on "black-box" models to better understand its performance. Our code is available at: https://github.com/satyamahesh84/SIDU_XAI_CODE.