Learning sparse auto-encoders for green AI image coding

Recently, convolutional auto-encoders (CAE) were introduced for image coding. They achieved performance improvements over the state-of-the-art JPEG2000 method. However, these performances were obtained using massive CAEs featuring a large number of parameters and whose training required heavy computational power. In this paper, we address the problem of lossy image compression using a CAE with a small memory footprint and low computational power usage. In order to overcome the computational cost issue, the majority of the literature uses Lagrangian proximal regularization methods, which are time consuming themselves. In this work, we propose a constrained approach and a new structured sparse learning method. We design an algorithm and test it on three constraints: the classical ℓ1 constraint, the ℓ1,∞ and the new ℓ1,1 constraint. Experimental results show that the ℓ1,1 constraint provides the best structured sparsity, resulting in a high reduction of memory and computational cost, with similar rate-distortion performance as with dense networks.