Most deep neural networks (DNNs) consist fundamentally of convolutional
and/or fully connected layers, wherein the linear transform can be cast as the
product between a filter matrix and a data matrix obtained by arranging feature
tensors into columns. The lately proposed deformable butterfly (DeBut)
decomposes the filter matrix into generalized, butterflylike factors, thus
achieving network compression orthogonal to the traditional ways of pruning or
low-rank decomposition. This work reveals an intimate link between DeBut and a
systematic hierarchy of depthwise and pointwise convolutions, which explains
the empirically good performance of DeBut layers. By developing an automated
DeBut chain generator, we show for the first time the viability of homogenizing
a DNN into all DeBut layers, thus achieving an extreme sparsity and
compression. Various examples and hardware benchmarks verify the advantages of
All-DeBut networks. In particular, we show it is possible to compress a
PointNet to < 5% parameters with < 5% accuracy drop, a record not achievable by
other compression schemes.

通过将滤波矩阵分解为类似于蝴蝶的因子，DeBut 图层可以实现与传统剪枝或低秩分解不同的网络压缩，通过开发自动化的 DeBut 链生成器，首次实现了将 DNN 全面均匀化为所有的 DeBut 图层，从而实现极度稀疏化和压缩，并通过各种例子和硬件基准测试验证了 All-DeBut 网络的优势，特别地，我们展示了将一个 PointNet 压缩到小于 5% 的参数并且准确率下降小于 5％的可能性，这是其他压缩方案所无法实现的。