GroupedMixer: An Entropy Model with Group-wise Token-Mixers for Learned Image Compression

arXiv:2405.01170v1 Announce Type: new
Abstract: Transformer-based entropy models have gained prominence in recent years due to their superior ability to capture long-range dependencies in probability distribution estimation compared to convolution-based methods. However, previous transformer-based entropy models suffer from a sluggish coding process due to pixel-wise autoregression or duplicated computation during inference. In this paper, we propose a novel transformer-based entropy model called GroupedMixer, which enjoys both faster coding speed and better compression performance than previous transformer-based methods. Specifically, our approach …

abstract arxiv coding compression computation convolution cs.cv dependencies distribution eess.iv entropy however image pixel probability process token transformer type wise