IncepFormer：一种高效的基于金字塔池的语义分割初始Transformer
IncepFormer: Efficient Inception Transformer with Pyramid Pooling for Semantic Segmentation
摘要：
语义分割通常受益于全球范围内，精细的本地化信息，多尺度功能等，以推进基于转换器的分割器与这些方面，我们提出了一个简单而强大的语义分割架构，称为IncepFormer。IncepFormer有以下两个关键贡献。首先，它介绍了一种新的金字塔结构的Transformer编码器，收获全球的背景和罚款本地化功能同时进行。这些特征被连接并馈送到卷积层中以进行最终的每像素预测。其次，IncepFormer集成了一个类似Inception-like的架构，具有深度卷积，并且在每个自注意层中集成了一个轻量级的前馈模块，有效地获得了丰富的局部多尺度对象特征。在五个基准上进行的大量实验表明，我们的IncepFormer在准确性和速度方面都优于最先进的方法，例如，1)我们的IncepFormer-S在ADE 20 K上实现了47.7%的mIoU，比现有的最佳方法高出1%，而仅花费一半的参数和更少的FLOP。2)我们的IncepFormer-B最终在具有39.6M参数的Cityscapes数据集上实现了82.0%的mIoU。代码可用：github.com/shendu0321/IncepFormer。
英文摘要：
Semantic segmentation usually benefits from global contexts, fine localisation information, multi-scale features, etc. To advance Transformer-based segmenters with these aspects, we present a simple yet powerful semantic segmentation architecture, termed as IncepFormer. IncepFormer has two critical contributions as following. First, it introduces a novel pyramid structured Transformer encoder which harvests global context and fine localisation features simultaneously. These features are concatenated and fed into a convolution layer for final per-pixel prediction. Second, IncepFormer integrates an Inception-like architecture with depth-wise convolutions, and a light-weight feed-forward module in each self-attention layer, efficiently obtaining rich local multi-scale object features. Extensive experiments on five benchmarks show that our IncepFormer is superior to state-of-the-art methods in both accuracy and speed, e.g., 1) our IncepFormer-S achieves 47.7% mIoU on ADE20K which outperforms the existing best method by 1% while only costs half parameters and fewer FLOPs. 2) Our IncepFormer-B finally achieves 82.0% mIoU on Cityscapes dataset with 39.6M parameters. Code is available:github.com/shendu0321/IncepFormer.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
