CrossFi: A Cross Domain Wi-Fi Sensing Framework Based on Siamese Network

2024-08-20

arXiv.org

AI Summary

Wi-Fi sensing models suffer from poor cross-scenario generalization due to domain shift, limiting adaptability to unseen environments or novel classes. To address this, we propose CrossFi, a cross-domain Wi-Fi sensing framework built upon a siamese network architecture. Its core innovations include: (i) CSi-Net—a novel similarity modeling module that replaces conventional distance metrics with an attention-enhanced mechanism; and (ii) Weight-Net—a dynamic class-template generator enabling effective zero-shot cross-domain and few-shot novel-class recognition. Experiments demonstrate state-of-the-art performance: 98.17% accuracy for in-domain gesture recognition, 91.72% for one-shot cross-domain recognition, 64.81% for zero-shot cross-domain recognition, and 84.75% for one-shot novel-class recognition—surpassing all existing methods across all settings.

Technology Category

• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web applications in cross-disciplinary domains and verticals such as mixed reality, smart cities, and digital health
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

In recent years, Wi-Fi sensing has garnered significant attention due to its numerous benefits, such as privacy protection, low cost, and penetration ability. Extensive research has been conducted in this field, focusing on areas such as gesture recognition, people identification, and fall detection. However, many data-driven methods encounter challenges related to domain shift, where the model fails to perform well in environments different from the training data. One major factor contributing to this issue is the limited availability of Wi-Fi sensing datasets, which makes models learn excessive irrelevant information and over-fit to the training set. Unfortunately, collecting large-scale Wi-Fi sensing datasets across diverse scenarios is a challenging task. To address this problem, we propose CrossFi, a siamese network-based approach that excels in both in-domain scenario and cross-domain scenario, including few-shot, zero-shot scenarios, and even works in few-shot new-class scenario where testing set contains new categories. The core component of CrossFi is a sample-similarity calculation network called CSi-Net, which improves the structure of the siamese network by using an attention mechanism to capture similarity information, instead of simply calculating the distance or cosine similarity. Based on it, we develop an extra Weight-Net that can generate a template for each class, so that our CrossFi can work in different scenarios. Experimental results demonstrate that our CrossFi achieves state-of-the-art performance across various scenarios. In gesture recognition task, our CrossFi achieves an accuracy of 98.17% in in-domain scenario, 91.72% in one-shot cross-domain scenario, 64.81% in zero-shot cross-domain scenario, and 84.75% in one-shot new-class scenario. The code for our model is publicly available at https://github.com/RS2002/CrossFi.

Problem

• Adaptability
• Wi-Fi Sensing
• Generalization

Innovation

• CrossFi
• CSi-Net
• Weight-Net