对比五种CNN架构，发现动态卷积在多任务中更高效准确
Cross-Task Benchmarking of CNN Architectures
- 基于ResNet-18改造五种动态卷积结构，引入注意力机制
- 在三个数据集上，动态方法精度与效率均优于传统CNN
- 适合研究多模态数据的模型设计与性能优化
本研究对多种动态卷积神经网络（CNN）在图像分类、分割和时间序列分析等任务中的表现进行了对比。以ResNet-18为基础，比较了五种变体：标准CNN、硬注意力CNN、局部与全局特征注意力的软注意力CNN，以及全向卷积（ODConv）。在Tiny ImageNet、Pascal VOC和UCR时间序列分类存档上的实验表明，注意力机制与动态卷积方法在准确率、效率和计算性能方面均持续优于传统CNN。ODConv在形态复杂的图像上尤为有效，能动态适应不同空间模式。动态CNN通过自适应核调制增强了特征表达与跨任务泛化能力。本研究为多模态数据的先进CNN架构设计提供了洞见，并指明了神经网络工程的潜在方向。
原文摘要 · Abstract (English)
This project provides a comparative study of dynamic convolutional neural networks (CNNs) for various tasks, including image classification, segmentation, and time series analysis. Based on the ResNet-18 architecture, we compare five variants of CNNs: the vanilla CNN, the hard attention-based CNN, the soft attention-based CNN with local (pixel-wise) and global (image-wise) feature attention, and the omni-directional CNN (ODConv). Experiments on Tiny ImageNet, Pascal VOC, and the UCR Time Series Classification Archive illustrate that attention mechanisms and dynamic convolution methods consistently exceed conventional CNNs in accuracy, efficiency, and computational performance. ODConv was especially effective on morphologically complex images by being able to dynamically adjust to varying spatial patterns. Dynamic CNNs enhanced feature representation and cross-task generalization through adaptive kernel modulation. This project provides perspectives on advanced CNN design architecture for multiplexed data modalities and indicates promising directions in neural network engineering.
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。