Open Access

ARTICLE

CAMSNet: Few-Shot Semantic Segmentation via Class Activation Map and Self-Cross Attention Block

Jingjing Yan¹, Xuyang Zhuang^2,*, Xuezhuan Zhao^1,2, Xiaoyan Shao^1,*, Jiaqi Han¹

1 School of Computer Science, Zhengzhou University of Aeronautics, Zhengzhou, 450046, China
2 National Key Laboratory of Air-Based Information Perception and Fusion, China Airborne Missile Academy, Luoyang, 471000, China

* Corresponding Authors: Xuyang Zhuang. Email: ; Xiaoyan Shao. Email:

(This article belongs to the Special Issue: Novel Methods for Image Classification, Object Detection, and Segmentation)

Computers, Materials & Continua 2025, 82(3), 5363-5386. https://doi.org/10.32604/cmc.2025.059709

Received 15 October 2024; Accepted 30 December 2024; Issue published 06 March 2025

Abstract

The key to the success of few-shot semantic segmentation (FSS) depends on the efficient use of limited annotated support set to accurately segment novel classes in the query set. Due to the few samples in the support set, FSS faces challenges such as intra-class differences, background (BG) mismatches between query and support sets, and ambiguous segmentation between the foreground (FG) and BG in the query set. To address these issues, The paper propose a multi-module network called CAMSNet, which includes four modules: the General Information Module (GIM), the Class Activation Map Aggregation (CAMA) module, the Self-Cross Attention (SCA) Block, and the Feature Fusion Module (FFM). In CAMSNet, The GIM employs an improved triplet loss, which concatenates word embedding vectors and support prototypes as anchors, and uses local support features of FG and BG as positive and negative samples to help solve the problem of intra-class differences. Then for the first time, the Class Activation Map (CAM) from the Weakly Supervised Semantic Segmentation (WSSS) is applied to FSS within the CAMA module. This method replaces the traditional use of cosine similarity to locate query information. Subsequently, the SCA Block processes the support and query features aggregated by the CAMA module, significantly enhancing the understanding of input information, leading to more accurate predictions and effectively addressing BG mismatch and ambiguous FG-BG segmentation. Finally, The FFM combines general class information with the enhanced query information to achieve accurate segmentation of the query image. Extensive Experiments on and demonstrate that the CAMSNet yields superior performance and set a state-of-the-art.

---

Keywords

---