论文标题
CADYQ：图像超分辨率的内容感知动态量化
CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution
论文作者
论文摘要
尽管具有卷积神经网络（CNN）的图像超分辨率（SR）的突破性进步，但由于SR网络的计算复杂性很高，SR尚未享受无处不在的应用。量化是解决此问题的有前途的方法之一。但是，现有的方法无法量化低于8位的位宽度的SR模型，由于固定的位宽度量化量的固定量，到处都有严重的准确性损失。在这项工作中，为了实现较高的平均比例减少，精度损失较低，我们建议针对SR网络的新颖内容感知的动态量化（CADYQ）方法，该方法根据输入图像的局部内容，将最佳位分配给本地区域和层。为此，引入了一个可训练的位选择器模块，以确定每一层和给定的本地图像补丁的适当位宽度和量化水平。该模块受量化灵敏度的控制，该量化通过使用贴片的图像梯度的平均幅度和层的输入特征的标准偏差来估计。拟议的量化管道已在各种SR网络上进行了测试，并对几个标准基准进行了广泛评估。计算复杂性和升高恢复精度的显着降低清楚地表明了SR提出的CADYQ框架的有效性。代码可在https://github.com/cheeun/cadyq上找到。
Despite breakthrough advances in image super-resolution (SR) with convolutional neural networks (CNNs), SR has yet to enjoy ubiquitous applications due to the high computational complexity of SR networks. Quantization is one of the promising approaches to solve this problem. However, existing methods fail to quantize SR models with a bit-width lower than 8 bits, suffering from severe accuracy loss due to fixed bit-width quantization applied everywhere. In this work, to achieve high average bit-reduction with less accuracy loss, we propose a novel Content-Aware Dynamic Quantization (CADyQ) method for SR networks that allocates optimal bits to local regions and layers adaptively based on the local contents of an input image. To this end, a trainable bit selector module is introduced to determine the proper bit-width and quantization level for each layer and a given local image patch. This module is governed by the quantization sensitivity that is estimated by using both the average magnitude of image gradient of the patch and the standard deviation of the input feature of the layer. The proposed quantization pipeline has been tested on various SR networks and evaluated on several standard benchmarks extensively. Significant reduction in computational complexity and the elevated restoration accuracy clearly demonstrate the effectiveness of the proposed CADyQ framework for SR. Codes are available at https://github.com/Cheeun/CADyQ.
