Generating visual explanations from deep networks using implicit neural representations

TL;DR

This paper introduces a novel approach using implicit neural representations to generate visual explanations for deep networks, improving interpretability by producing well-behaved and multiple attribution masks.

Contribution

It demonstrates that INRs can effectively generate visual attribution masks and extend extremal perturbations, offering new insights into deep model behavior.

Findings

Implicit neural representations produce well-behaved attribution masks.

The method can generate multiple non-overlapping masks for the same image.

INRs reveal that models associate labels with both objects and contextual textures.

Abstract

Explaining deep learning models in a way that humans can easily understand is essential for responsible artificial intelligence applications. Attribution methods constitute an important area of explainable deep learning. The attribution problem involves finding parts of the network's input that are the most responsible for the model's output. In this work, we demonstrate that implicit neural representations (INRs) constitute a good framework for generating visual explanations. Firstly, we utilize coordinate-based implicit networks to reformulate and extend the extremal perturbations technique and generate attribution masks. Experimental results confirm the usefulness of our method. For instance, by proper conditioning of the implicit network, we obtain attribution masks that are well-behaved with respect to the imposed area constraints. Secondly, we present an iterative INR-based method that can be used to generate multiple non-overlapping attribution masks for the same image. We depict that a deep learning model may associate the image label with both the appearance of the object of interest as well as with areas and textures usually accompanying the object. Our study demonstrates that implicit networks are well-suited for the generation of attribution masks and can provide interesting insights about the performance of deep learning models.