# Performance degradation of ImageNet trained models by simple image transformations

Source: [Performance degradation of ImageNet trained models by simple image transformations](<https://www.sota2.com/research/paper/68fa6cfe1e209131cea372a8>)

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

Data updated: 2025-10-27T06:16:31.054Z

Authors: Harsh Maheshwari

Published: 2022-07-17T05:23:48.000Z

## Abstract

ImageNet trained PyTorch models are generally preferred as the off-the-shelf models for direct use or for initialisation in most computer vision tasks. In this paper, we simply test a representative set of these convolution and transformer based models under many simple image transformations like horizontal shifting, vertical shifting, scaling, rotation, presence of Gaussian noise, cutout, horizontal flip and vertical flip and report the performance drop caused by such transformations. We find that even simple transformations like rotating the image by 10{\\deg} or zooming in by 20% can reduce the top-1 accuracy of models like ResNet152 by 1%+. The code is available at https://github.com/harshm121/imagenet-transformation-degradation.

## 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/2207.08079>)

[PDF](<https://arxiv.org/pdf/2207.08079.pdf>)