论文标题
用于深图像压缩的通道级变量量化网络
Channel-Level Variable Quantization Network for Deep Image Compression
论文作者
论文摘要
深图像压缩系统主要包含四个组件：编码器，量化，熵模型和解码器。为了优化这四个组件，提出了一个联合速率延伸框架，许多基于神经网络的深层方法在图像压缩方面取得了巨大成功。但是，几乎所有基于卷积神经网络的方法都同样处理通道特征图，从而降低了处理不同类型信息的灵活性。在本文中，我们提出了一个通道级变量量化网络，以动态分配更多的比特率，以为重要的通道分配更多的比特率，并为可忽略不计的通道撤回比特率。具体而言，我们提出了一个可变量化控制器。它由两个关键组成部分组成：通道重要性模块，它们可以在训练过程中动态地学习通道的重要性以及拆卸合并模块，该模块可以为不同的通道分配不同的比特率。我们还将量化器提出为高斯混合模型的方式。定量和定性实验验证了所提出的模型的有效性，并证明我们的方法可以实现卓越的性能，并可以产生更好的视觉重建。
Deep image compression systems mainly contain four components: encoder, quantizer, entropy model, and decoder. To optimize these four components, a joint rate-distortion framework was proposed, and many deep neural network-based methods achieved great success in image compression. However, almost all convolutional neural network-based methods treat channel-wise feature maps equally, reducing the flexibility in handling different types of information. In this paper, we propose a channel-level variable quantization network to dynamically allocate more bitrates for significant channels and withdraw bitrates for negligible channels. Specifically, we propose a variable quantization controller. It consists of two key components: the channel importance module, which can dynamically learn the importance of channels during training, and the splitting-merging module, which can allocate different bitrates for different channels. We also formulate the quantizer into a Gaussian mixture model manner. Quantitative and qualitative experiments verify the effectiveness of the proposed model and demonstrate that our method achieves superior performance and can produce much better visual reconstructions.
