BriefGPT.xyz
Nov, 2024
少样本学习中的语义像素匹配的分层特征度量
Layer-Wise Feature Metric of Semantic-Pixel Matching for Few-Shot Learning
HTML
PDF
Hao Tang, Junhao Lu, Guoheng Huang, Ming Li, Xuhang Chen...
TL;DR
本研究针对传统少样本学习中基于全局度量的相似性计算的不足,提出了分层特征度量的语义像素匹配方法(LWFM-SPM)。该方法通过分层嵌入模块和语义像素匹配模块实现了对图像对之间关键像素的精细对齐,显著提升了模型在多个少样本分类基准上的性能。
Abstract
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 acros
→