Watermarking Images in Self-Supervised Latent Spaces - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year :

Watermarking Images in Self-Supervised Latent Spaces

Pierre Fernandez
  • Function : Author
Alexandre Sablayrolles
  • Function : Author
Hervé Jégou
  • Function : Author
Matthijs Douze
  • Function : Author


We revisit watermarking techniques based on pre-trained deep networks, in the light of self-supervised approaches. We present a way to embed both marks and binary messages into their latent spaces, leveraging data augmentation at marking time. Our method can operate at any resolution and creates watermarks robust to a broad range of transformations (rotations, crops, JPEG, contrast, etc). It significantly outperforms the previous zero-bit methods, and its performance on multi-bit watermarking is on par with state-of-the-art encoder-decoder architectures trained end-to-end for watermarking. The code is available at github.com/facebookresearch/ssl_watermarking.
Fichier principal
Vignette du fichier
Pierre_Icassp.pdf (902.03 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03591396 , version 1 (28-02-2022)


  • HAL Id : hal-03591396 , version 1


Pierre Fernandez, Alexandre Sablayrolles, Teddy Furon, Hervé Jégou, Matthijs Douze. Watermarking Images in Self-Supervised Latent Spaces. ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE, May 2022, Singapore, Singapore. pp.1-5. ⟨hal-03591396⟩
62 View
75 Download


Gmail Facebook Twitter LinkedIn More