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.

翻译：新兴的学习压缩（LC）技术用深度神经网络（DNN）替代传统编解码模块，并通过端到端训练优化率失真性能。该方法被视为未来图像/视频压缩的发展方向，大量研究致力于提升其压缩效率。然而，现有工作多通过设计更复杂的DNN结构来提升压缩效率，这导致计算复杂度显著增加。本文另辟蹊径，提出通过充分利用现有DNN容量来改进压缩性能。具体而言，我们引导潜在特征学习更丰富多样化的特征集，从而实现更优的重建质量。我们设计了一种通道级特征解相关损失函数，并将其集成到LC优化框架中。本文提出并评估了三种策略，分别优化（1）变换网络、（2）上下文模型和（3）两者联合优化。在两种主流LC方法上的实验结果表明，本方法在零复杂度增量下实现了最高8.06%的BD-Rate压缩性能提升。该方案可作为即插即用解决方案，用于优化任何类似的LC方法。