通过分层像素语义匹配，提升少样本学习中的相似度计算精度
Layer-Wise Feature Metric of Semantic-Pixel Matching for Few-Shot Learning
- 分层嵌入模块优化图像对跨相关性，生成聚焦特征图
- 语义像素匹配模块用分配算法对齐关键像素，减少空间错位
- 在4个主流数据集上表现优异，适合少样本图像分类场景
在少样本学习中，传统基于度量的方法常依赖全局度量计算相似性。然而，在自然场景中，关键实例的空间布局在不同图像间往往不一致，导致语义像素错配，造成相似度测量不准。为此，我们提出一种新方法——分层特征语义像素匹配度量（LWFM-SPM），通过两个关键模块提升模型性能：(1) 分层嵌入（LWE）模块，优化图像对的交叉相关性，为每一层生成聚焦的特征图；(2) 语义像素匹配（SPM）模块，基于语义嵌入使用分配算法对齐关键像素。我们在四个广泛使用的少样本分类基准（miniImageNet、tieredImageNet、CUB-200-2011、CIFAR-FS）上进行了大量实验，结果表明LWFM-SPM在各基准上均取得具有竞争力的性能。代码将公开于https://github.com/Halo2Tang/Code-for-LWFM-SPM。
原文摘要 · Abstract (English)
In Few-Shot Learning (FSL), traditional metric-based approaches often rely on global metrics to compute similarity. However, in natural scenes, the spatial arrangement of key instances is often inconsistent across images. This spatial misalignment can result in mismatched semantic pixels, leading to inaccurate similarity measurements. To address this issue, we propose a novel method called the Layer-Wise Features Metric of Semantic-Pixel Matching (LWFM-SPM) to make finer comparisons. Our method enhances model performance through two key modules: (1) the Layer-Wise Embedding (LWE) Module, which refines the cross-correlation of image pairs to generate well-focused feature maps for each layer; (2)the Semantic-Pixel Matching (SPM) Module, which aligns critical pixels based on semantic embeddings using an assignment algorithm. We conducted extensive experiments to evaluate our method on four widely used few-shot classification benchmarks: miniImageNet, tieredImageNet, CUB-200-2011, and CIFAR-FS. The results indicate that LWFM-SPM achieves competitive performance across these benchmarks. Our code will be publicly available on https://github.com/Halo2Tang/Code-for-LWFM-SPM.
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。