arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.08079cs.CVcs.LG
收藏

通过简单图像变换的ImageNet训练模型的性能退化

Performance degradation of ImageNet trained models by simple image transformations

Georgia Institute of Technology(佐治亚理工学院)

Harsh Maheshwari

摘要:

ImageNet训练的PyTorch模型通常是首选的现成模型,用于直接使用或在大多数计算机视觉任务中进行初始化。在本文中,我们简单地测试了这些卷积和基于Transformer的模型的代表集,在许多简单的图像变换下,如水平移动,垂直移动,缩放,旋转,高斯噪声的存在,剪切,水平翻转和垂直翻转,并报告了由这些变换引起的性能下降。我们发现,即使是像旋转图像10°或放大20%这样的简单变换,也会使ResNet 152等模型的top-1精度降低1%以上。该代码可在https://github.com/harshm121/imagenet-transformation-degradation上获得。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑