论文标题
探索神经图像压缩中的结构稀疏性
Exploring Structural Sparsity in Neural Image Compression
论文作者
论文摘要
神经图像压缩已达到或超出传统方法（例如JPEG，BPG，WebP）。但是，他们具有级联卷积层的复杂网络结构为实践部署带来了沉重的计算负担。在本文中，我们探讨了神经图像压缩网络中的结构稀疏性，以获得实时加速，而无需任何专门的硬件设计或算法。我们建议一个简单的插件自适应二进制频道掩蔽（ABCM）来判断每个卷积通道的重要性，并在训练过程中引入稀疏性。在推断期间，修剪不重要的通道以获得较小的网络和更少的计算。我们将我们的方法实施到具有不同熵模型以验证其有效性和泛化的三个神经图像压缩网络中，实验结果表明，通过可忽略的性能下降，可以达到高达7倍的计算和3倍加速度。
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.
