# Prototype Generation: Robust Feature Visualisation for Data Independent Interpretability

Source: [Prototype Generation: Robust Feature Visualisation for Data Independent Interpretability](<https://www.sota2.com/research/paper/68fa70bb1e209131cea4cedc>)

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

Data updated: 2025-10-26T01:48:53.779Z

Authors: Arush Tagade, Jessica Rumbelow

Published: 2023-09-29T11:16:06.000Z

## Abstract

We introduce Prototype Generation, a stricter and more robust form of feature visualisation for model-agnostic, data-independent interpretability of image classification models. We demonstrate its ability to generate inputs that result in natural activation paths, countering previous claims that feature visualisation algorithms are untrustworthy due to the unnatural internal activations. We substantiate these claims by quantitatively measuring similarity between the internal activations of our generated prototypes and natural images. We also demonstrate how the interpretation of generated prototypes yields important insights, highlighting spurious correlations and biases learned by models which quantitative methods over test-sets cannot identify.

## 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/2309.17144>)

[PDF](<https://arxiv.org/pdf/2309.17144.pdf>)