# CAREC: Continual Wireless Action Recognition with Expansion–Compression Coordination

## TL;DR

CAREC is a system that improves wireless action recognition by adapting to new actions without forgetting old ones, using expansion and compression techniques.

## Contribution

The novel CAREC framework balances model expansion and compression for continual learning in wireless action recognition.

## Key findings

- CAREC reduces performance degradation by 51.82% across four incremental stages.
- The model achieves 67.84% accuracy with 21.08 M parameters, 80% smaller than conventional models.
- Balanced knowledge distillation and data replay help retain performance while adding new classes.

## Abstract

In real-world applications, user demands for new functionalities and activities constantly evolve, requiring action recognition systems to incrementally incorporate new action classes without retraining from scratch. This class-incremental learning (CIL) paradigm is essential for enabling adaptive and scalable systems that can grow over time. However, Wi-Fi-based indoor action recognition under incremental learning faces two major challenges: catastrophic forgetting of previously learned knowledge and uncontrolled model expansion as new classes are added. To address these issues, we propose CAREC, a class-incremental framework that balances dynamic model expansion with efficient compression. CAREC adopts a multi-branch architecture to incorporate new classes without compromising previously learned features and leverages balanced knowledge distillation to compress the model by 80% while preserving performance. A data replay strategy retains representative samples of old classes, and a super-feature extractor enhances inter-class discrimination. Evaluated on the large-scale XRF55 dataset, CAREC reduces performance degradation by 51.82% over four incremental stages and achieves 67.84% accuracy with only 21.08 M parameters, 20% parameters compared to conventional approaches.