# Interpretable Discovery in Large Image Data Sets

Source: [Interpretable Discovery in Large Image Data Sets](<https://www.sota2.com/research/paper/68fa647d1e209131cea04d0a>)

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

Data updated: 2025-10-28T13:56:36.114Z

Authors: Kiri L. Wagstaff, Jake Lee

Published: 2018-06-21T17:30:26.000Z

## Abstract

Automated detection of new, interesting, unusual, or anomalous images within large data sets has great value for applications from surveillance (e.g., airport security) to science (observations that don't fit a given theory can lead to new discoveries). Many image data analysis systems are turning to convolutional neural networks (CNNs) to represent image content due to their success in achieving high classification accuracy rates. However, CNN representations are notoriously difficult for humans to interpret. We describe a new strategy that combines novelty detection with CNN image features to achieve rapid discovery with interpretable explanations of novel image content. We applied this technique to familiar images from ImageNet as well as to a scientific image collection from planetary science.

## 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/1806.08340>)

[PDF](<https://arxiv.org/pdf/1806.08340.pdf>)