In this paper we propose the macroblock scaling (MBS) algorithm, which can be
applied to various CNN architectures to reduce their model size. MBS adaptively
reduces each CNN macroblock depending on its information redundancy measured by
our proposed effective flops. Empirical studies conducted with ImageNet and
CIFAR-10 attest that MBS can reduce the model size of some already compact CNN
models, e.g., MobileNetV2 (25.03% further reduction) and ShuffleNet (20.74%),
and even ultra-deep ones such as ResNet-101 (51.67%) and ResNet-1202 (72.71%)
with negligible accuracy degradation. MBS also performs better reduction at a
much lower cost than the state-of-the-art optimization-based methods do. MBS's
simplicity and efficiency, its flexibility to work with any CNN model, and its
scalability to work with models of any depth make it an attractive choice for
CNN model size reduction.

本文提出了一种宏块缩放算法 (MBS)，可适用于各种 CNN 体系结构，以减小其模型大小。通过与 ImageNet 和 CIFAR-10 的经验研究表明，MBS 可以进一步减小某些已经紧凑的 CNN 模型的模型大小，同时即使是超深的 ResNet-101 和 ResNet-1202 也可以减小其模型大小，而准确度降低可忽略不计。MBS 的简洁高效性，其与任何 CNN 模型一起使用的灵活性以及与任何深度的模型一起使用的可扩展性使其成为 CNN 模型大小缩小的有吸引力的选择。