Channel-Level Variable Quantization Network for Deep Image Compression
-
- Zhisheng Zhong
- The University of Tokyo
-
- Hiroaki Akutsu
- Hitachi, Ltd.
-
- Kiyoharu Aizawa
- The University of Tokyo
Description
<jats:p>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.</jats:p>
Journal
-
- Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
-
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence 2020-07
International Joint Conferences on Artificial Intelligence Organization