论文标题
通过简单的图像转换对Imagenet训练模型的性能退化
Performance degradation of ImageNet trained models by simple image transformations
论文作者
论文摘要
经过Imagenet训练有素的Pytorch型号通常是直接使用或在大多数计算机视觉任务中进行初始化的现成模型。在本文中，我们只需在许多简单的图像变换下测试这些卷积和基于变压器模型的代表性集，例如水平转换，垂直转移，缩放，旋转，高斯噪声，切口，切割，水平翻转和垂直翻转，并报告由这种转换引起的性能下降。我们发现，即使是简单的转换，例如将图像旋转10°或放大20％也可以将Resnet152（例如Resnet152）的前1个精度降低1％+。该代码可在https://github.com/harshm121/imagenet-transformation-degradation上找到。
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° 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.
