%0 Journal Article %1 yang2020improving %A Yang, Yibo %A Bamler, Robert %A Mandt, Stephan %D 2020 %K compression inference variational %T Improving Inference for Neural Image Compression %U http://arxiv.org/abs/2006.04240 %X We consider the problem of lossy image compression with deep latent variable models. State-of-the-art methods build on hierarchical variational autoencoders~(VAEs) and learn inference networks to predict a compressible latent representation of each data point. Drawing on the variational inference perspective on compression, we identify three approximation gaps which limit performance in the conventional approach: (i)~an amortization gap, (ii)~a discretization gap, and (iii)~a marginalization gap. We propose improvements to each of these three shortcomings based on iterative inference, stochastic annealing for discrete optimization, and bits-back coding, resulting in the first application of bits-back coding to lossy compression. In our experiments, which include extensive baseline comparisons and ablation studies, we achieve new state-of-the-art performance on lossy image compression using an established VAE architecture, by changing only the inference method.

@article{yang2020improving, abstract = {We consider the problem of lossy image compression with deep latent variable models. State-of-the-art methods build on hierarchical variational autoencoders~(VAEs) and learn inference networks to predict a compressible latent representation of each data point. Drawing on the variational inference perspective on compression, we identify three approximation gaps which limit performance in the conventional approach: (i)~an amortization gap, (ii)~a discretization gap, and (iii)~a marginalization gap. We propose improvements to each of these three shortcomings based on iterative inference, stochastic annealing for discrete optimization, and bits-back coding, resulting in the first application of bits-back coding to lossy compression. In our experiments, which include extensive baseline comparisons and ablation studies, we achieve new state-of-the-art performance on lossy image compression using an established VAE architecture, by changing only the inference method.}, added-at = {2020-06-09T09:28:03.000+0200}, author = {Yang, Yibo and Bamler, Robert and Mandt, Stephan}, biburl = {https://www.bibsonomy.org/bibtex/26adb4ef2be36b803f38b997a81e79720/kirk86}, description = {[2006.04240] Improving Inference for Neural Image Compression}, interhash = {d3174d993212808be2ddf6eb6a0c668b}, intrahash = {6adb4ef2be36b803f38b997a81e79720}, keywords = {compression inference variational}, note = {cite arxiv:2006.04240Comment: 8 pages + detailed supplement with additional qualitative and quantitative results}, timestamp = {2020-06-09T09:28:03.000+0200}, title = {Improving Inference for Neural Image Compression}, url = {http://arxiv.org/abs/2006.04240}, year = 2020 }