HLIC: Harmonizing Optimization Metrics in Learned Image Compression by Reinforcement Learning

Abstract

Learned image compression is making good progress in recent years. Peak signal-to-noise ratio (PSNR) and multiscale structural similarity (MS-SSIM) are the two most popular evaluation metrics. As different metrics only reflect certain aspects of human perception, works in this field normally optimize two models using PSNR and MS-SSIM as loss function separately, which is suboptimal and makes it difficult to select the model with best visual quality or overall performance. Towards solving this problem, we propose to Harmonize optimization metrics in Learned Image Compression (HLIC) using online loss function adaptation by reinforcement learning. By doing so, we are able to leverage the advantages of both PSNR and MS-SSIM, achieving better visual quality and higher VMAF score. To our knowledge, our work is the first to explore automatic loss function adaptation for harmonizing optimization metrics in low level vision tasks like learned image compression.

Evaluation of Sampling Algorithms for a Pairwise Subjective Assessment Methodology

“…However, this study does not include GAN adversarial losses. Sun et al [13] leverage the advantage of using both MSE and MS-SSIM in the loss function through an online loss function adaptation by reinforcement learning. In [13], the trade-off between PSNR and MS-SSIM is controlled to achieve better visual quality, as measured by the VMAF metric.…”

“…Sun et al [13] leverage the advantage of using both MSE and MS-SSIM in the loss function through an online loss function adaptation by reinforcement learning. In [13], the trade-off between PSNR and MS-SSIM is controlled to achieve better visual quality, as measured by the VMAF metric. Chen et al [14] proposed an alternative optimization strategy by introducing a proxy neural network as a surrogate for the non-differentiable perceptual quality metric (VMAF) [15].…”