Exploring Structural Sparsity in Neural Image Compression
This addresses the deployment challenge of neural image compression for practical applications, though it is incremental as it builds on existing methods.
The paper tackles the heavy computational burden of neural image compression networks by exploring structural sparsity to achieve real-time acceleration, resulting in up to 7x computation reduction and 3x acceleration with negligible performance drop.
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.