Mark My Words: Dangers of Watermarked Images in ImageNet

• URL: http://arxiv.org/abs/2303.05498v1
• Date: Thu, 9 Mar 2023 18:51:31 GMT
• Title: Mark My Words: Dangers of Watermarked Images in ImageNet
• Authors: Kirill Bykov, Klaus-Robert M\"uller, Marina M.-C. H\"ohne
• Abstract summary: A significant number of images in the ImageNet dataset contain watermarks. A variety of ImageNet classes, such as "monitor", "broom", "apron" and "safe" rely on spurious correlations. We propose a simple approach to mitigate this issue in fine-tuned networks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Npix2Cpix: A GAN-Based Image-to-Image Translation Network With Retrieval- Classification Integration for Watermark Retrieval From Historical Document Images [1.3549498237473223]
  The identification and restoration of ancient watermarks has long been a major topic in codicology and history. This paper proposes a modified U-net-based conditional generative adversarial network (GAN) named Npix2Cpix to translate noisy raw historical watermarked images into clean, handwriting-free watermarked images.
  arXiv  Detail & Related papers  (2024-06-05T18:10:49Z)
• A self-supervised CNN for image watermark removal [102.94929746450902]
  We propose a self-supervised convolutional neural network (CNN) in image watermark removal (SWCNN) SWCNN uses a self-supervised way to construct reference watermarked images rather than given paired training samples, according to watermark distribution. Taking into account texture information, a mixed loss is exploited to improve visual effects of image watermark removal.
  arXiv  Detail & Related papers  (2024-03-09T05:59:48Z)
• Perceptive self-supervised learning network for noisy image watermark removal [59.440951785128995]
  We propose a perceptive self-supervised learning network for noisy image watermark removal (PSLNet) Our proposed method is very effective in comparison with popular convolutional neural networks (CNNs) for noisy image watermark removal.
  arXiv  Detail & Related papers  (2024-03-04T16:59:43Z)
• Docmarking: Real-Time Screen-Cam Robust Document Image Watermarking [97.77394585669562]
  Proposed approach does not try to prevent leak in the first place but rather aims to determine source of the leak. Method works by applying on the screen a unique identifying watermark as semi-transparent image. Watermark image is static and stays on the screen all the time thus watermark present on every captured photograph of the screen.
  arXiv  Detail & Related papers  (2023-04-25T09:32:11Z)
• Semantic-Aware Generation for Self-Supervised Visual Representation Learning [116.5814634936371]
  We advocate for Semantic-aware Generation (SaGe) to facilitate richer semantics rather than details to be preserved in the generated image. SaGe complements the target network with view-specific features and thus alleviates the semantic degradation brought by intensive data augmentations. We execute SaGe on ImageNet-1K and evaluate the pre-trained models on five downstream tasks including nearest neighbor test, linear classification, and fine-scaled image recognition.
  arXiv  Detail & Related papers  (2021-11-25T16:46:13Z)
• Robust Watermarking using Diffusion of Logo into Autoencoder Feature Maps [10.072876983072113]
  In this paper, we propose to use an end-to-end network for watermarking. We use a convolutional neural network (CNN) to control the embedding strength based on the image content. Different image processing attacks are simulated as a network layer to improve the robustness of the model.
  arXiv  Detail & Related papers  (2021-05-24T05:18:33Z)
• Split then Refine: Stacked Attention-guided ResUNets for Blind Single Image Visible Watermark Removal [69.92767260794628]
  Previous watermark removal methods require to gain the watermark location from users or train a multi-task network to recover the background indiscriminately. We propose a novel two-stage framework with a stacked attention-guided ResUNets to simulate the process of detection, removal and refinement. We extensively evaluate our algorithm over four different datasets under various settings and the experiments show that our approach outperforms other state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2020-12-13T09:05:37Z)
• VirTex: Learning Visual Representations from Textual Annotations [25.104705278771895]
  VirTex is a pretraining approach using semantically dense captions to learn visual representations. We train convolutional networks from scratch on COCO Captions, and transfer them to downstream recognition tasks. On all tasks, VirTex yields features that match or exceed those learned on ImageNet -- supervised or unsupervised.
  arXiv  Detail & Related papers  (2020-06-11T17:58:48Z)
• Focus Longer to See Better:Recursively Refined Attention for Fine-Grained Image Classification [148.4492675737644]
  Deep Neural Network has shown great strides in the coarse-grained image classification task. In this paper, we try to focus on these marginal differences to extract more representative features. Our network repetitively focuses on parts of images to spot small discriminative parts among the classes.
  arXiv  Detail & Related papers  (2020-05-22T03:14:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.