Autoencoder based image compression: can the learning be quantization independent? - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Autoencoder based image compression: can the learning be quantization independent?

Résumé

This paper explores the problem of learning transforms for image compression via autoencoders. Usually, the rate-distortion performances of image compression are tuned by varying the quantization step size. In the case of autoen-coders, this in principle would require learning one transform per rate-distortion point at a given quantization step size. Here, we show that comparable performances can be obtained with a unique learned transform. The different rate-distortion points are then reached by varying the quantization step size at test time. This approach saves a lot of training time.
Fichier principal
Vignette du fichier
autoencoder_based.pdf (559.32 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01713644 , version 1 (22-02-2018)

Identifiants

Citer

Thierry Dumas, Aline Roumy, Christine Guillemot. Autoencoder based image compression: can the learning be quantization independent?. ICASSP 2018 - International Conference on Acoustics, Speech and Signal Processing ICASSP, Apr 2018, Calgary, Canada. pp.1188-1192, ⟨10.1109/ICASSP.2018.8462263⟩. ⟨hal-01713644⟩
526 Consultations
1062 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More