论文标题
Factorizenet：在量化约束下进行有效网络体系结构探索的渐进深度分解
FactorizeNet: Progressive Depth Factorization for Efficient Network Architecture Exploration Under Quantization Constraints
论文作者
论文摘要
深度分解和量化已成为设计有效的深卷积神经网络（CNN）体系结构的两种主要策略，该体系结构量身定制，用于在边缘上进行低功率推断。但是，对不同的深度分解选择如何影响CNN中每一层的最终分布，尤其是在量化的权重和激活的情况下，仍然几乎没有详细的理解。在这项研究中，我们在量化约束下介绍了有效的CNN体系结构探索的进行性深度分解策略。通过以渐进的方式增加算法的深度分解粒度，提出的策略可以对层的分布进行细粒度的低级分析。因此，在固定精确量化下，可以对效率 - 准确性权衡的深入增长，层级级别的见解。这样的渐进深度分解策略还可以根据所需的效率 - 准确性要求有效地识别最佳深度型宏观结构设计（我们在这里将其称为Factorizenet）。
Depth factorization and quantization have emerged as two of the principal strategies for designing efficient deep convolutional neural network (CNN) architectures tailored for low-power inference on the edge. However, there is still little detailed understanding of how different depth factorization choices affect the final, trained distributions of each layer in a CNN, particularly in the situation of quantized weights and activations. In this study, we introduce a progressive depth factorization strategy for efficient CNN architecture exploration under quantization constraints. By algorithmically increasing the granularity of depth factorization in a progressive manner, the proposed strategy enables a fine-grained, low-level analysis of layer-wise distributions. Thus enabling the gain of in-depth, layer-level insights on efficiency-accuracy tradeoffs under fixed-precision quantization. Such a progressive depth factorization strategy also enables efficient identification of the optimal depth-factorized macroarchitecture design (which we will refer to here as FactorizeNet) based on the desired efficiency-accuracy requirements.
