# Measuring and improving the quality of visual explanations

Source: [Measuring and improving the quality of visual explanations](<https://www.sota2.com/research/paper/68fa67361e209131cea14dc9>)

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

Data updated: 2025-10-25T22:09:20.078Z

Authors: Agnieszka Grabska-Barwi\\'nska

Published: 2020-03-14T00:52:00.000Z

## Abstract

The ability of to explain neural network decisions goes hand in hand with their safe deployment. Several methods have been proposed to highlight features important for a given network decision. However, there is no consensus on how to measure effectiveness of these methods. We propose a new procedure for evaluating explanations. We use it to investigate visual explanations extracted from a range of possible sources in a neural network. We quantify the benefit of combining these sources and challenge a recent appeal for taking bias parameters into account. We support our conclusions with a general assessment of the impact of bias parameters in ImageNet classifiers

## 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/2003.08774>)

[PDF](<https://arxiv.org/pdf/2003.08774.pdf>)