快速高性能学习图像压缩：改进的棋盘格上下文模型、可变形残差模块与知识蒸馏
Fast and High-Performance Learned Image Compression With Improved Checkerboard Context Model, Deformable Residual Module, and Knowledge Distillation
AI总结：
本文提出四种技术（可变形卷积、改进棋盘格上下文模型、三步知识蒸馏和L1正则化）平衡图像压缩复杂度与性能，实现比现有方法快20倍编码和70-90倍解码，同时R-D性能提升2.3%。
摘要：
基于深度学习的图像压缩近年来取得了巨大进展。然而，许多领先的方案使用串行上下文自适应熵模型来提高率失真（R-D）性能，但这非常缓慢。此外，编码和解码网络的复杂度相当高，不适合许多实际应用。在本文中，我们引入了四种技术来平衡复杂度与性能之间的权衡。我们首次在压缩框架中引入可变形卷积模块，该模块可以去除输入图像中更多的冗余，从而增强压缩性能。其次，我们设计了一个具有两个独立分布参数估计网络和不同概率模型的棋盘格上下文模型，与串行上下文自适应模型相比，在不牺牲性能的情况下实现了并行解码。第三，我们开发了一种改进的三步知识蒸馏和训练方案，以实现解码器网络复杂度与性能之间的不同权衡，该方案将教师网络的最终和中间结果都传递给学生网络以帮助其训练。第四，我们引入$L_{1}$正则化使潜在表示的数值更加稀疏。然后我们仅在编码和解码过程中编码非零通道，这可以大大减少编码和解码时间。实验表明，与最先进的学习图像编码方案相比，我们的方法在编码速度上快约20倍，在解码速度上快70-90倍，且我们的R-D性能也高出$2.3\%$。在Kodak和Tecnick-40数据集上测试时，我们的方法在PSNR和MS-SSIM指标上优于传统方法H.266/VVC-intra（4:4:4）以及一些领先的学习方案。
英文摘要：
Deep learning-based image compression has made great progresses recently. However, many leading schemes use serial context-adaptive entropy model to improve the rate-distortion (R-D) performance, which is very slow. In addition, the complexities of the encoding and decoding networks are quite high and not suitable for many practical applications. In this paper, we introduce four techniques to balance the trade-off between the complexity and performance. We are the first to introduce deformable convolutional module in compression framework, which can remove more redundancies in the input image, thereby enhancing compression performance. Second, we design a checkerboard context model with two separate distribution parameter estimation networks and different probability models, which enables parallel decoding without sacrificing the performance compared to the sequential context-adaptive model. Third, we develop an improved three-step knowledge distillation and training scheme to achieve different trade-offs between the complexity and the performance of the decoder network, which transfers both the final and intermediate results of the teacher network to the student network to help its training. Fourth, we introduce $L_{1}$ regularization to make the numerical values of the latent representation more sparse. Then we only encode non-zero channels in the encoding and decoding process, which can greatly reduce the encoding and decoding time. Experiments show that compared to the state-of-the-art learned image coding scheme, our method can be about 20 times faster in encoding and 70-90 times faster in decoding, and our R-D performance is also $2.3 \%$ higher. Our method outperforms the traditional approach in H.266/VVC-intra (4:4:4) and some leading learned schemes in terms of PSNR and MS-SSIM metrics when testing on Kodak and Tecnick-40 datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
