arXiv:2508.03625cs.CVcs.AI2025-08ICCV被引 5

Attention Zoom让卷积网络更专注关键区域,提升图像识别精度。

AttZoom: Attention Zoom for Better Visual Features

  • 添加独立注意力层,聚焦输入图像重要区域。
  • 在CIFAR-100和TinyImageNet上提升分类准确率。
  • 无需修改模型结构,适配各类卷积网络。

我们提出Attention Zoom,一种模块化且模型无关的空间注意力机制,用于改进卷积神经网络(CNN)的特征提取。与需要特定架构集成的传统注意力方法不同,该方法引入一个独立层,对输入中的高重要性区域进行空间强调。我们在多个CNN主干网络上使用CIFAR-100和TinyImageNet进行了评估,结果显示在Top-1和Top-5分类准确率上均有稳定提升。通过Grad-CAM和空间扭曲可视化分析发现,该方法能激发细粒度且多样的注意力模式。结果证实,该注意力层在几乎不增加架构开销的情况下,显著提升了CNN的性能,具有良好的有效性与通用性。

原文摘要 · Abstract (English)

We present Attention Zoom, a modular and model-agnostic spatial attention mechanism designed to improve feature extraction in convolutional neural networks (CNNs). Unlike traditional attention approaches that require architecture-specific integration, our method introduces a standalone layer that spatially emphasizes high-importance regions in the input. We evaluated Attention Zoom on multiple CNN backbones using CIFAR-100 and TinyImageNet, showing consistent improvements in Top-1 and Top-5 classification accuracy. Visual analyses using Grad-CAM and spatial warping reveal that our method encourages fine-grained and diverse attention patterns. Our results confirm the effectiveness and generality of the proposed layer for improving CCNs with minimal architectural overhead.

注意力机制卷积网络特征提取

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。