This paper presents a Spatial Re-parameterization (SpRe) method for the N:M
sparsity in CNNs. SpRe is stemmed from an observation regarding the restricted
variety in spatial sparsity present in N:M sparsity compared with unstructured
sparsity. Particularly, N:M sparsity exhibits a fixed sparsity rate within the
spatial domains due to its distinctive pattern that mandates N non-zero
components among M successive weights in the input channel dimension of
convolution filters. On the contrary, we observe that unstructured sparsity
displays a substantial divergence in sparsity across the spatial domains, which
we experimentally verified to be very crucial for its robust performance
retention compared with N:M sparsity. Therefore, SpRe employs the
spatial-sparsity distribution of unstructured sparsity to assign an extra
branch in conjunction with the original N:M branch at training time, which
allows the N:M sparse network to sustain a similar distribution of spatial
sparsity with unstructured sparsity. During inference, the extra branch can be
further re-parameterized into the main N:M branch, without exerting any
distortion on the sparse pattern or additional computation costs. SpRe has
achieved a commendable feat by matching the performance of N:M sparsity methods
with state-of-the-art unstructured sparsity methods across various benchmarks.
Code and models are anonymously available at
https://github.com/zyxxmu/SpRe.

本文提出了 Spatial Re-parameterization (SpRe) 方法，用于 N:M 稀疏性在 CNN 中的应用。该方法可以在训练期间利用非结构化稀疏性的空间稀疏性分布来为 N:M 稀疏性模型分配一个额外的支路，使其可以维持类似于非结构化稀疏性的空间稀疏性分布。在推理期间，该额外的支路可以进一步重新参数化为主要的 N:M 支路，而不会对稀疏模式或额外的计算成本产生扭曲。SpRe 方法可以在各种基准测试中匹配 N:M 稀疏性方法的表现与最先进的非结构化稀疏性方法。