StaticSegFormer：基于静态结构化剪枝的高效高性能语义分割方法
StaticSegFormer: An Efficient High-Performance Semantic Segmentation Based on Static Structured Pruning
中文总结 AI 辅助
该研究针对动态结构化剪枝在GPU上帧率低的问题，提出StaticSegFormer静态结构化剪枝方法，使SegFormer在Cityscapes上帧率提升最高34%且无mIoU下降，适配小型编码器与大图像场景。
中文摘要 AI 辅助
结构化剪枝通过在推理阶段消除参数组提升深度神经网络（DNN）的效率。现有方法大多仅降低计算复杂度（FLOPs），而语义分割性能（mIoU）略有下降。近期动态结构化剪枝方法旨在减少性能下降，同时进一步降低FLOPs。但在ADE20K和Cityscapes基准上，本研究发现：在GPU平台上，这类动态方法的帧率低得出人意料，远低于简单的静态方法，且mIoU和FLOPs表现相当。为解决该问题，本文提出一种针对注意力层的静态结构化剪枝方法，可同时实现更低的FLOPs和SegFormer网络的高帧率，在Cityscapes数据集上帧率相对提升最高达34%，且完全无mIoU性能下降。本文提出的StaticSegFormer方法在小型编码器和大图像场景中表现最优。
英文摘要
Structured pruning enhances the efficiency of deep neural networks (DNNs) by eliminating groups of parameters during inference. Previous methods mostly reduce computational complexity (FLOPs), while semantic segmentation performance (mIoU) slightly drops. Accordingly, recent dynamic structured pruning methods aim at reducing the performance drop, while lowering the FLOPs even more. However, on the ADE20K and Cityscapes benchmarks, our study reveals that on a GPU platform such dynamic methods exhibit a surprisingly low frame rate far below a simple static approach, while having comparable results in mIoU and FLOPs. To address this issue, we propose a static structured pruning method for attention layers, that achieves both, a lower FLOPs and a high frame rate [fps] of the SegFormer network, the latter increased by up to 34% relative on the Cityscapes dataset, while having no mIoU performance drop at all. Our so-called StaticSegFormer method is strongest for small encoders and large images.
