PAMS：通过参数化最大尺度的量化超分辨率
PAMS: Quantized Super-Resolution via Parameterized Max Scale
摘要：
深度卷积神经网络（DCNN）在超分辨率（SR）任务中表现出了主导性能。然而，其沉重的内存成本和计算开销显着限制了其在资源有限的设备上的实际部署，这主要是由于浮点存储和权重与激活之间的操作。虽然先前的努力主要采取定点操作，量化权重和激活与固定的编码长度可能会导致显着的性能下降，特别是在低比特。具体而言，大多数没有批量归一化的最先进的SR模型具有大的动态量化范围，这也是性能下降的另一个原因。为了解决这两个问题，我们提出了一个新的量化方案，称为PAMS（PAMS），它适用于可训练截断参数探索自适应的量化范围的上限。最后，引入结构化知识转移（SKT）损失对量化网络进行微调。大量的实验表明，所提出的PAMS方案可以很好地压缩和加速现有的SR模型，如EDSR和RDN。值得注意的是，8位PAMS-EDSR在Set 5基准测试中将PSNR从32.095dB提高到32.124dB，具有2.42 $\times$压缩比，达到了新的最先进水平。
英文摘要：
Deep convolutional neural networks (DCNNs) have shown dominant performance in the task of super-resolution (SR). However, their heavy memory cost and computation overhead significantly restrict their practical deployments on resource-limited devices, which mainly arise from the floating-point storage and operations between weights and activations. Although previous endeavors mainly resort to fixed-point operations, quantizing both weights and activations with fixed coding lengths may cause significant performance drop, especially on low bits. Specifically, most state-of-the-art SR models without batch normalization have a large dynamic quantization range, which also serves as another cause of performance drop. To address these two issues, we propose a new quantization scheme termed PArameterized Max Scale (PAMS), which applies the trainable truncated parameter to explore the upper bound of the quantization range adaptively. Finally, a structured knowledge transfer (SKT) loss is introduced to fine-tune the quantized network. Extensive experiments demonstrate that the proposed PAMS scheme can well compress and accelerate the existing SR models such as EDSR and RDN. Notably, 8-bit PAMS-EDSR improves PSNR on Set5 benchmark from 32.095dB to 32.124dB with 2.42$\times$ compression ratio, which achieves a new state-of-the-art.
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。
