Tiled Squeeze-and-Excite：具有局部空间背景的通道注意力
Tiled Squeeze-and-Excite: Channel Attention With Local Spatial Context
摘要：
在本文中，我们调查的空间上下文所需的通道注意。为此，我们研究了流行的挤压和激发（SE）块，这是一个简单而轻量级的通道注意力机制。SE块及其众多变体通常使用全局平均池（GAP）为每个通道创建单个描述符。在这里，我们经验性地分析了有效的通道注意所需的空间上下文的量，并发现在原始图像的七行或列的顺序上的有限的localcontext足以匹配全局上下文的性能。我们提出了平铺挤压和激发（TSE），这是一个框架，用于构建SE样块，每个通道采用几个描述符，每个描述符仅基于本地上下文。我们进一步表明，TSE是SE块的替代品，可以在现有的SE网络中使用，而无需重新训练。这意味着局部上下文描述符彼此相似并且与全局上下文描述符相似。最后，我们表明，TSE具有重要的实际意义，部署SE网络的低AI加速器，由于其减少管道缓冲的要求。例如，与SE相比，使用TSE将EfficientDetD2中的激活管道缓冲量减少了90%（从50M减少到4.77M），而不会损失准确性。我们的代码和预训练模型将公开提供。
英文摘要：
In this paper we investigate the amount of spatial context required for channel attention. To this end we study the popular squeeze-and-excite (SE) block which is a simple and lightweight channel attention mechanism. SE blocks and its numerous variants commonly use global average pooling (GAP) to create a single descriptor for each channel. Here, we empirically analyze the amount of spatial context needed for effective channel attention and find that limited localcontext on the order of seven rows or columns of the original image is sufficient to match the performance of global context. We propose tiled squeeze-and-excite (TSE), which is a framework for building SE-like blocks that employ several descriptors per channel, with each descriptor based on local context only. We further show that TSE is a drop-in replacement for the SE block and can be used in existing SE networks without re-training. This implies that local context descriptors are similar both to each other and to the global context descriptor. Finally, we show that TSE has important practical implications for deployment of SE-networks to dataflow AI accelerators due to their reduced pipeline buffering requirements. For example, using TSE reduces the amount of activation pipeline buffering in EfficientDetD2 by 90% compared to SE (from 50M to 4.77M) without loss of accuracy. Our code and pre-trained models will be publicly available.
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。
