提出轻量通道注意力模块，高效提升CNN性能
Lightweight Channel Attention for Efficient CNNs
- 用自适应一维卷积与分组操作设计轻量注意力模块
- 在ResNet18上达94.68%准确率，参数效率媲美ECA
- 适合移动端等资源受限场景的模型优化
注意力机制已成为现代卷积神经网络的重要组成部分，在计算开销极小的情况下显著提升性能。然而，不同通道注意力设计在效率与精度之间的权衡仍缺乏深入探索。本文通过实证研究比较了Squeeze and Excitation (SE)、Efficient Channel Attention (ECA) 以及提出的Lite Channel Attention (LCA) 模块，在ResNet18和MobileNetV2架构上基于CIFAR-10数据集的表现。LCA采用自适应一维卷积结合分组操作，大幅减少参数量的同时保持有效的注意力行为。实验结果表明，LCA在ResNet18上达到94.68%的准确率，在MobileNetV2上达到93.10%，在参数效率上与ECA相当，并维持良好的推理延迟。全面的基准测试涵盖FLOPs、参数量和GPU延迟，为资源受限环境部署增强注意力的CNN提供了实用参考。
原文摘要 · Abstract (English)
Attention mechanisms have become integral to modern convolutional neural networks (CNNs), delivering notable performance improvements with minimal computational overhead. However, the efficiency accuracy trade off of different channel attention designs remains underexplored. This work presents an empirical study comparing Squeeze and Excitation (SE), Efficient Channel Attention (ECA), and a proposed Lite Channel Attention (LCA) module across ResNet 18 and MobileNetV2 architectures on CIFAR 10. LCA employs adaptive one dimensional convolutions with grouped operations to reduce parameter usage while preserving effective attention behavior. Experimental results show that LCA achieves competitive accuracy, reaching 94.68 percent on ResNet 18 and 93.10 percent on MobileNetV2, while matching ECA in parameter efficiency and maintaining favorable inference latency. Comprehensive benchmarks including FLOPs, parameter counts, and GPU latency measurements are provided, offering practical insights for deploying attention enhanced CNNs in resource constrained environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。