SCSC：增强 CNN 与 Transformer 的空间跨尺度卷积模块
SCSC: Spatial Cross-scale Convolution Module to Strengthen both CNNs and Transformers
AI总结：
本文提出空间跨尺度卷积模块 SCSC，通过高效跨尺度编码与空间嵌入增强局部和多尺度特征，在人脸识别及 ImageNet 上以更低或相近计算量提升 CNN 与 Transformer。
摘要：
本文提出了一个名为空间跨尺度卷积（Spatial Cross-scale Convolution，SCSC）的模块，该模块经证实能够有效改进 CNN 和 Transformer。如今，CNN 与 Transformer 已在多种任务中取得成功。尤其是 Transformer，越来越多的工作在计算机视觉领域实现了最先进性能。因此，研究人员开始探索这些架构的机制。大感受野、稀疏连接、权重共享和动态权重被认为是设计有效基础模型的关键。然而，仍有一些问题有待解决：大型密集卷积核和自注意力效率低下，而且大感受野使其难以捕捉局部特征。受上述分析启发并为解决所提到的问题，本文设计了一个融合这些设计关键要素的通用模块，以同时增强 CNN 和 Transformer。SCSC 引入了高效的空间跨尺度编码器和空间嵌入模块，在单层中捕捉多种特征。在人脸识别任务上，搭载 SCSC 的 FaceResNet 可提升 2.7%，同时 FLOPs 减少 68%、参数减少 79%。在 ImageNet 分类任务上，搭载 SCSC 的 Swin Transformer 可在 FLOPs 减少 22% 的情况下取得更优性能，而搭载 CSCS 的 ResNet 可在复杂度相近的情况下提升 5.3%。此外，嵌入 SCSC 的传统网络（例如 ResNet）能够达到与 Swin Transformer 相当的性能。
英文摘要：
This paper presents a module, Spatial Cross-scale Convolution (SCSC), which is verified to be effective in improving both CNNs and Transformers. Nowadays, CNNs and Transformers have been successful in a variety of tasks. Especially for Transformers, increasing works achieve state-of-the-art performance in the computer vision community. Therefore, researchers start to explore the mechanism of those architectures. Large receptive fields, sparse connections, weight sharing, and dynamic weight have been considered keys to designing effective base models. However, there are still some issues to be addressed: large dense kernels and self-attention are inefficient, and large receptive fields make it hard to capture local features. Inspired by the above analyses and to solve the mentioned problems, in this paper, we design a general module taking in these design keys to enhance both CNNs and Transformers. SCSC introduces an efficient spatial cross-scale encoder and spatial embed module to capture assorted features in one layer. On the face recognition task, FaceResNet with SCSC can improve 2.7% with 68% fewer FLOPs and 79% fewer parameters. On the ImageNet classification task, Swin Transformer with SCSC can achieve even better performance with 22% fewer FLOPs, and ResNet with CSCS can improve 5.3% with similar complexity. Furthermore, a traditional network (e.g., ResNet) embedded with SCSC can match Swin Transformer's performance.
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。
