# Gradient Weighted Superpixels for Interpretability in CNNs

Source: [Gradient Weighted Superpixels for Interpretability in CNNs](<https://www.sota2.com/research/paper/68fa66421e209131cea0f46f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:46:30.691Z

Authors: Thomas Hartley, Kirill Sidorov, Christopher Willis, David Marshall

Published: 2019-08-16T12:02:25.000Z

## Abstract

As Convolutional Neural Networks embed themselves into our everyday lives, the need for them to be interpretable increases. However, there is often a trade-off between methods that are efficient to compute but produce an explanation that is difficult to interpret, and those that are slow to compute but provide a more interpretable result. This is particularly challenging in problem spaces that require a large input volume, especially video which combines both spatial and temporal dimensions. In this work we introduce the idea of scoring superpixels through the use of gradient based pixel scoring techniques. We show qualitatively and quantitatively that this is able to approximate LIME, in a fraction of the time. We investigate our techniques using both image classification, and action recognition networks on large scale datasets (ImageNet and Kinetics-400 respectively).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1908.08997>)

[PDF](<https://arxiv.org/pdf/1908.08997.pdf>)