Open Access

ARTICLE

Two-Stage Category-Guided Frequency Modulation for Few-Shot Semantic Segmentation

Yiming Tang^*, Yanqiu Chen

School of Computer Science, Fudan University, Shanghai, 200438, China

* Corresponding Author: Yiming Tang. Email:

Computers, Materials & Continua 2025, 83(2), 1707-1726. https://doi.org/10.32604/cmc.2025.062412

Received 18 December 2024; Accepted 18 February 2025; Issue published 16 April 2025

Abstract

Semantic segmentation of novel object categories with limited labeled data remains a challenging problem in computer vision. Few-shot segmentation methods aim to address this problem by recognizing objects from specific target classes with a few provided examples. Previous approaches for few-shot semantic segmentation typically represent target classes using class prototypes. These prototypes are matched with the features of the query set to get segmentation results. However, class prototypes are usually obtained by applying global average pooling on masked support images. Global pooling discards much structural information, which may reduce the accuracy of model predictions. To address this issue, we propose a Category-Guided Frequency Modulation (CGFM) method. CGFM is designed to learn category-specific information in the frequency space and leverage it to provide a two-stage guidance for the segmentation process. First, to self-adaptively activate class-relevant frequency bands while suppressing irrelevant ones, we leverage the Dual-Perception Gaussian Band Pre-activation (DPGBP) module to generate Gaussian filters using class embedding vectors. Second, to further enhance category-relevant frequency components in activated bands, we design a Support-Guided Category Response Enhancement (SGCRE) module to effectively introduce support frequency components into the modulation of query frequency features. Experiments on the and datasets demonstrate the promising performance of our model. The code will be released at accessed on 17 February 2025.

---

Keywords

---