Abstract
The emerging Learned Compression (LC) replaces the traditional codec modules with Deep Neural Networks (DNN), which are trained end-to-end for rate-distortion performance. This approach is considered as the future of image/video compression, and major efforts have been dedicated to improving its compression efficiency. However, most proposed works target compression efficiency by employing more complex DNNS, which contributes to higher computational complexity. Alternatively, this paper proposes to improve compression by fully exploiting the existing DNN capacity. To do so, the latent features are guided to learn a richer and more diverse set of features, which corresponds to better reconstruction. A channel-wise feature decorrelation loss is designed and is integrated into the LC optimization. Three strategies are proposed and evaluated, which optimize (1) the transformation network, (2) the context model, and (3) both networks. Experimental results on two established LC methods show that the proposed method improves the compression with a BD-Rate of up to 8.06%, with no added complexity. The proposed solution can be applied as a plug-and-play solution to optimize any similar LC method.
Abstract (translated)
学习压缩(LC)作为一种新兴的压缩技术,取代了传统的编码模块,使用了深度神经网络(DNN),这些网络是针对码率失真性能进行端到端训练的。这种方法被认为是图像/视频压缩的未来,并且为提高其压缩效率做出了主要努力。然而,大多数提出的作品通过采用更复杂的DNN来提高压缩效率,导致计算复杂度更高。相反,本文提出了一种通过充分利用现有DNN能力来提高压缩的方法。为此,将潜在特征指导学习更丰富和更多样化的特征,从而实现更好的重构。在LC优化中,设计了一个通道级特征相关损失,并将其集成进去。提出了三种策略并对其进行了评估,它们分别是优化(1)转换网络,(2)上下文模型,(3)两个网络。在两个已有的LC方法上进行实验,结果表明,与所提出的方法相比,压缩率提高了至少8.06%,而没有增加复杂性。所提出的解决方案可以作为一个可插拔的解决方案,用于优化任何类似的LC方法。
URL
https://arxiv.org/abs/2403.10936