The utilization of pre-trained networks, especially those trained on ImageNet, has become a common practice in Computer Vision. However, prior research has indicated that a significant number of images in the ImageNet dataset contain watermarks, making pre-trained networks susceptible to learning artifacts such as watermark patterns within their latent spaces. In this paper, we aim to assess the extent to which popular pre-trained architectures display such behavior and to determine which classes are most affected. Additionally, we examine the impact of watermarks on the extracted features. Contrary to the popular belief that the Chinese logographic watermarks impact the "carton" class only, our analysis reveals that a variety of ImageNet classes, such as "monitor", "broom", "apron" and "safe" rely on spurious correlations. Finally, we propose a simple approach to mitigate this issue in fine-tuned networks by ignoring the encodings from the feature-extractor layer of ImageNet pre-trained networks that are most susceptible to watermark imprints.

翻译：利用预训练网络（尤其是基于ImageNet训练的模型）已成为计算机视觉领域的常见做法。然而，先前研究表明，ImageNet数据集中大量图像含有水印，这使得预训练网络容易在其潜在空间中学习到水印模式等伪影。本文旨在评估主流预训练架构在多大程度上表现出此类行为，并确定受影响最严重的类别。此外，我们研究了水印对提取特征的影响。与普通认为中文表意文字水印仅影响“纸箱”类别的观点相反，我们的分析揭示，ImageNet中的多种类别（如“显示器”、“扫帚”、“围裙”和“保险箱”）依赖于虚假相关性。最后，我们提出一种简单方法，通过在微调网络中忽略ImageNet预训练网络中最易受水印印记影响的特征提取器层的编码，来缓解此问题。