Parameter-Efficient Domain Adaption for CSI Crowd-Counting via Self-Supervised Learning with Adapter Modules

2026-01-05

arXiv.org

AI Summary

This work addresses the performance degradation of WiFi channel state information (CSI)-based device-free crowd counting in cross-environment deployments due to domain shift. To mitigate this, the authors propose a two-stage framework: first, a CSI-ResNet-A backbone is pretrained via self-supervised contrastive learning to extract domain-invariant features; second, a lightweight Adapter module is introduced for efficient fine-tuning, coupled with a stateful counting machine to produce stable occupancy estimates. Innovatively integrating Adapters with self-supervised learning for CSI-based counting, the method achieves 99% of the performance of full-parameter fine-tuning while updating only 2.8% of the model parameters. The approach attains a mean absolute error (MAE) of 0.44 on WiFlow (with 10 samples) and 98.8% accuracy on WiAR, and introduces a Generalizability Index (GI) to quantitatively assess model robustness.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Device-free crowd-counting using WiFi Channel State Information (CSI) is a key enabling technology for a new generation of privacy-preserving Internet of Things (IoT) applications. However, practical deployment is severely hampered by the domain shift problem, where models trained in one environment fail to generalise to another. To overcome this, we propose a novel two-stage framework centred on a CSI-ResNet-A architecture. This model is pre-trained via self-supervised contrastive learning to learn domain-invariant representations and leverages lightweight Adapter modules for highly efficient fine-tuning. The resulting event sequence is then processed by a stateful counting machine to produce a final, stable occupancy estimate. We validate our framework extensively. On our WiFlow dataset, our unsupervised approach excels in a 10-shot learning scenario, achieving a final Mean Absolute Error (MAE) of just 0.44--a task where supervised baselines fail. To formally quantify robustness, we introduce the Generalisation Index (GI), on which our model scores near-perfectly, confirming its ability to generalise. Furthermore, our framework sets a new state-of-the-art public WiAR benchmark with 98.8\% accuracy. Our ablation studies reveal the core strength of our design: adapter-based fine-tuning achieves performance within 1\% of a full fine-tune (98.84\% vs. 99.67\%) while training 97.2\% fewer parameters. Our work provides a practical and scalable solution for developing robust sensing systems ready for real-world IoT deployments.

Problem

• domain shift
• crowd counting
• Channel State Information
• generalization
• device-free sensing

Innovation

• Parameter-Efficient Adaptation
• Self-Supervised Learning
• Adapter Modules
• Domain Generalization
• CSI Crowd Counting