# Do ImageNet Classifiers Generalize to ImageNet?

Source: [Do ImageNet Classifiers Generalize to ImageNet?](<https://www.sota2.com/research/paper/68fa65e21e209131cea0d27e>)

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

Data updated: 2025-10-25T21:38:30.146Z

Authors: Benjamin Recht, Rebecca Roelofs, Ludwig Schmidt, Vaishaal Shankar

Published: 2019-02-13T20:35:44.000Z

## Abstract

We build new test sets for the CIFAR-10 and ImageNet datasets. Both benchmarks have been the focus of intense research for almost a decade, raising the danger of overfitting to excessively re-used test sets. By closely following the original dataset creation processes, we test to what extent current classification models generalize to new data. We evaluate a broad range of models and find accuracy drops of 3% - 15% on CIFAR-10 and 11% - 14% on ImageNet. However, accuracy gains on the original test sets translate to larger gains on the new test sets. Our results suggest that the accuracy drops are not caused by adaptivity, but by the models' inability to generalize to slightly "harder" images than those found in the original test sets.

## 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/1902.10811>)

[PDF](<https://arxiv.org/pdf/1902.10811.pdf>)