LSGQuant: 层敏感性引导的量化方法用于一步扩散现实视频超分辨率
LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-Resolution
AI总结：
LSGQuant 通过动态范围自适应量化器和层敏感性引导策略，实现了一步扩散现实视频超分辨率的高效量化方法，显著提升了模型压缩效果。
摘要：
一步扩散模型在现实视频超分辨率（VSR）中展现了 promising 的能力和快速的推理速度。然而，扩散变压器（DiTs）的显著模型大小和高计算成本限制了下游应用。尽管低比特量化是模型压缩的常见方法，但量化模型的有效性受到输入潜在特征的高动态范围和各层行为差异的挑战。为了解决这些挑战，我们引入了 LSGQuant，一种针对一步扩散现实 VSR 的层敏感性引导量化方法。我们的方法结合了动态范围自适应量化器（DRAQ）以适应视频令牌激活。此外，我们通过校准中逐层统计分析来估计层敏感性，并实现一种以方差为导向的层训练策略（VOLTS）。我们还引入了量化感知优化（QAO）以联合优化量化分支和保留的高精度分支。广泛的实验表明，我们的方法在全精度模型中几乎具有相同的性能，并显著超过了现有量化技术。代码可在：https://github.com/zhengchen1999/LSGQuant 上获得。
英文摘要：
One-Step Diffusion Models have demonstrated promising capability and fast inference in video super-resolution (VSR) for real-world. Nevertheless, the substantial model size and high computational cost of Diffusion Transformers (DiTs) limit downstream applications. While low-bit quantization is a common approach for model compression, the effectiveness of quantized models is challenged by the high dynamic range of input latent and diverse layer behaviors. To deal with these challenges, we introduce LSGQuant, a layer-sensitivity guided quantizing approach for one-step diffusion-based real-world VSR. Our method incorporates a Dynamic Range Adaptive Quantizer (DRAQ) to fit video token activations. Furthermore, we estimate layer sensitivity and implement a Variance-Oriented Layer Training Strategy (VOLTS) by analyzing layer-wise statistics in calibration. We also introduce Quantization-Aware Optimization (QAO) to jointly refine the quantized branch and a retained high-precision branch. Extensive experiments demonstrate that our method has nearly performance to origin model with full-precision and significantly exceeds existing quantization techniques. Code is available at: https://github.com/zhengchen1999/LSGQuant.
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。
