# A Method for Restoring the Training Set Distribution in an Image Classifier

Source: [A Method for Restoring the Training Set Distribution in an Image Classifier](<https://www.sota2.com/research/paper/68fa640c1e209131cea024c4>)

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

Data updated: 2025-10-25T20:55:10.976Z

Authors: Alexey Chaplygin, Joshua Chacksfield

Published: 2018-02-05T14:49:06.000Z

## Abstract

Convolutional Neural Networks are a well-known staple of modern image classification. However, it can be difficult to assess the quality and robustness of such models. Deep models are known to perform well on a given training and estimation set, but can easily be fooled by data that is specifically generated for the purpose. It has been shown that one can produce an artificial example that does not represent the desired class, but activates the network in the desired way. This paper describes a new way of reconstructing a sample from the training set distribution of an image classifier without deep knowledge about the underlying distribution. This enables access to the elements of images that most influence the decision of a convolutional network and to extract meaningful information about the training distribution.

## 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/1802.01435>)

[PDF](<https://arxiv.org/pdf/1802.01435.pdf>)