Layer-Wise Feature Metric of Semantic-Pixel Matching for Few-Shot Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Hao, Lu, Junhao, Huang, Guoheng, Li, Ming, Chen, Xuhang, Zhong, Guo, Tan, Zhengguang, Li, Zinuo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910692793122816
author Tang, Hao
Lu, Junhao
Huang, Guoheng
Li, Ming
Chen, Xuhang
Zhong, Guo
Tan, Zhengguang
Li, Zinuo
author_facet Tang, Hao
Lu, Junhao
Huang, Guoheng
Li, Ming
Chen, Xuhang
Zhong, Guo
Tan, Zhengguang
Li, Zinuo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06363
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Layer-Wise Feature Metric of Semantic-Pixel Matching for Few-Shot Learning
Tang, Hao
Lu, Junhao
Huang, Guoheng
Li, Ming
Chen, Xuhang
Zhong, Guo
Tan, Zhengguang
Li, Zinuo
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title Layer-Wise Feature Metric of Semantic-Pixel Matching for Few-Shot Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2411.06363