MFPP: Morphological Fragmental Perturbation Pyramid for Black-Box Model Explanations

TL;DR

This paper introduces MFPP, a multi-scale perturbation method that effectively explains black-box DNN predictions by analyzing input image fragments without internal model knowledge.

Contribution

The novel MFPP method employs a pyramid of multi-scale image fragments for perturbation, improving black-box explanation accuracy over existing methods.

Findings

MFPP outperforms state-of-the-art black-box interpretability methods.

MFPP effectively identifies input regions responsible for DNN predictions.

The pyramid structure enhances the exploration of morphological features.

Abstract

Deep neural networks (DNNs) have recently been applied and used in many advanced and diverse tasks, such as medical diagnosis, automatic driving, etc. Due to the lack of transparency of the deep models, DNNs are often criticized for their prediction that cannot be explainable by human. In this paper, we propose a novel Morphological Fragmental Perturbation Pyramid (MFPP) method to solve the Explainable AI problem. In particular, we focus on the black-box scheme, which can identify the input area that is responsible for the output of the DNN without having to understand the internal architecture of the DNN. In the MFPP method, we divide the input image into multi-scale fragments and randomly mask out fragments as perturbation to generate a saliency map, which indicates the significance of each pixel for the prediction result of the black box model. Compared with the existing input sampling perturbation method, the pyramid structure fragment has proved to be more effective. It can better explore the morphological information of the input image to match its semantic information, and does not need any value inside the DNN. We qualitatively and quantitatively prove that MFPP meets and exceeds the performance of state-of-the-art (SOTA) black-box interpretation method on multiple DNN models and datasets.