MetaSeg：基于MetaFormer的全局上下文感知高效语义分割网络
MetaSeg: MetaFormer-based Global Contexts-aware Network for Efficient Semantic Segmentation
AI总结：
本研究针对语义分割任务，提出从骨干到解码器均采用MetaFormer架构的MetaSeg网络，通过通道缩减注意力模块兼顾效率与性能，在多个基准上以更低计算成本超越现有最优方法。
摘要：
在Transformer之外，探索如何挖掘MetaFormer（一种对Transformer性能提升至关重要的架构）的能力具有重要意义。以往研究仅将其用于骨干网络。与以往研究不同，我们在语义分割任务中更广泛地探索了MetaFormer架构的能力。我们提出了一种性能强大的语义分割网络MetaSeg，其从骨干网络到解码器均采用MetaFormer架构。我们的MetaSeg表明，MetaFormer架构不仅对骨干网络，对解码器捕获有用上下文也发挥着重要作用。此外，近期的分割方法研究显示，使用基于CNN的骨干网络提取空间信息、配合解码器提取全局信息，比采用基于Transformer的骨干网络搭配基于CNN的解码器效果更优。这促使我们采用搭载MetaFormer模块的基于CNN的骨干网络，并设计基于MetaFormer的解码器，该解码器包含一个用于捕获全局上下文的新型自注意力模块。为兼顾语义分割任务中全局上下文提取与自注意力的计算效率，我们提出了通道缩减注意力（Channel Reduction Attention, CRA）模块，该模块将查询和键的通道维度缩减至一维。通过这种方式，我们提出的MetaSeg在ADE20K、Cityscapes、COCO-stuff和Synapse等主流语义分割基准及医学图像分割基准上，以更低的计算成本超越了以往的最优方法。代码可在https://github.com/hyunwoo137/MetaSeg获取。
英文摘要：
Beyond the Transformer, it is important to explore how to exploit the capacity of the MetaFormer, an architecture that is fundamental to the performance improvements of the Transformer. Previous studies have exploited it only for the backbone network. Unlike previous studies, we explore the capacity of the Metaformer architecture more extensively in the semantic segmentation task. We propose a powerful semantic segmentation network, MetaSeg, which leverages the Metaformer architecture from the backbone to the decoder. Our MetaSeg shows that the MetaFormer architecture plays a significant role in capturing the useful contexts for the decoder as well as for the backbone. In addition, recent segmentation methods have shown that using a CNN-based backbone for extracting the spatial information and a decoder for extracting the global information is more effective than using a transformer-based backbone with a CNN-based decoder. This motivates us to adopt the CNN-based backbone using the MetaFormer block and design our MetaFormer-based decoder, which consists of a novel self-attention module to capture the global contexts. To consider both the global contexts extraction and the computational efficiency of the self-attention for semantic segmentation, we propose a Channel Reduction Attention (CRA) module that reduces the channel dimension of the query and key into the one dimension. In this way, our proposed MetaSeg outperforms the previous state-of-the-art methods with more efficient computational costs on popular semantic segmentation and a medical image segmentation benchmark, including ADE20K, Cityscapes, COCO-stuff, and Synapse. The code is available at https://github.com/hyunwoo137/MetaSeg.
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。
