An Efficient ConvNet for Learned Image Compression with Transformer-Style Architecture
Haihang Ruan, Feng Ryan Wang, Yan Wang · 2023
Recently, transformer-based and convolution-based methods have achieved significant results in learned image compression. By comparing the design of convolutional network (convnet) and transformers, we replace the self-attention with convolution to capture spatial and channel adaptability. We propose a simple attention module (SAM) with transformer style. Combining the proposed SAM with channel-wise and checkerboard entropy model, we propose an efficient end-to-end learned image compression method. It is a simple method but obtains strong result and efficient coding speed. Experiments demonstrate that our method achieves competitive results by comparing with previous learning-based methods and conventional image codecs.