2022/02/09 by Shanzhi Yin, Chao Li, Yin, Shanzhi +9 · 1 citation
Computer Science · #68U10(primary) #94A08 68T07(secondary) #Advanced Image Processing Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #I.2.6 #I.4.2 #Image and Signal Denoising Methods #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Neural Networks and Applications #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2202.04595
openalex publication_date 2022/02/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Neural image compression have reached or out-performed traditional methods (such as JPEG, BPG, WebP). However,their sophisticated network structures with cascaded convolution layers bring heavy computational burden for practical deployment. In this paper, we explore the structural sparsity in neural image compression network to obtain real-time acceleration without any specialized hardware design or algorithm. We propose a simple plug-in adaptive binary channel masking(ABCM) to judge the importance of each convolution channel and introduce sparsity during training. During inference, the unimportant channels are pruned to obtain slimmer network and less computation. We implement our method into three neural image compression networks with different entropy models to verify its effectiveness and generalization, the experiment results show that up to 7x computation reduction and 3x acceleration can be achieved with negligible performance drop.