A Neural Network Approach For Joint Optimization Of Predictors In Lifting-Based Image Coders - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

A Neural Network Approach For Joint Optimization Of Predictors In Lifting-Based Image Coders

Abstract

The objective of this paper is to investigate techniques for learning Fully Connected Network (FCN) models in a lifting based image coding scheme. More precisely, based on a 2D non separable lifting structure composed of three FCN-based prediction stages followed by an FCN-based update one, we first propose to resort to an p loss function, with p ∈ {1, 2}, to learn the three FCN prediction models. While the latter are separately learned in the first approach, a novel joint learning approach is then developed by minimizing a weighted p loss function related to the global prediction error. Experimental results, carried out on the standard Challenge Learned Image Compression (CLIC) dataset, show the benefits of the proposed techniques in terms of rate-distortion performance.
Fichier principal
Vignette du fichier
A_neural_network_approach_for_joint_optimization_of_predictors_in_lifting_based_image_coders.pdf (478.56 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03526467 , version 1 (14-01-2022)

Identifiers

Cite

Tassnim Dardouri, M. Kaaniche, A. Benazza-Benyahia, J.-C. Pesquet, G. Dauphin. A Neural Network Approach For Joint Optimization Of Predictors In Lifting-Based Image Coders. 2021 IEEE International Conference on Image Processing (ICIP), Sep 2021, Anchorage / Virtual, United States. pp.3747-3751, ⟨10.1109/ICIP42928.2021.9506737⟩. ⟨hal-03526467⟩
51 View
92 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More