PI-TTA: Physics-Informed Source-Free Test-Time Adaptation for Robust Human Activity Recognition on Mobile Devices

• URL: http://arxiv.org/abs/2604.25435v1
• Date: Tue, 28 Apr 2026 09:44:01 GMT
• Title: PI-TTA: Physics-Informed Source-Free Test-Time Adaptation for Robust Human Activity Recognition on Mobile Devices
• Abstract summary: Source-free test-time adaptation (TTA) is appealing for mobile and wearable sensing because it enables on-device personalization without centralizing private data.<n>We propose PI-TTA, a lightweight source-free adaptation framework that stabilizes online updates through three physics-consistent constraints.
• Score: 14.981641027538387
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Source-free test-time adaptation (TTA) is appealing for mobile and wearable sensing because it enables on-device personalization from unlabeled test streams without centralizing private data. However, sensor-based human activity recognition (HAR) poses challenges that are less pronounced in standard vision benchmarks: behavioral inertial streams are temporally correlated and often exhibit within-session shifts caused by sensor rotation, placement change, and sampling-rate drift. Under this streaming non-i.i.d. setting, widely used vision-style TTA objectives can become unstable, leading to overconfident errors, representation collapse, and catastrophic forgetting. We propose PI-TTA, a lightweight source-free adaptation framework that stabilizes online updates through three physics-consistent constraints: gravity consistency, short-horizon temporal continuity, and spectral stability. PI-TTA updates the same small parameter subset as strong source-free baselines and incurs only modest overhead, making it suitable for on-device deployment. Experiments on USCHAD, PAMAP2, and mHealth under long-sequence stress tests and factorized shift protocols show that PI-TTA mitigates the severe degradation observed in confidence-driven baselines and preserves stable adaptation under sustained streaming conditions. It improves long-sequence accuracy by up to 9.13% and reduces physical-violation rates by 27.5%, 24.1%, and 45.4% on USCHAD, PAMAP2, and mHealth, respectively. These results demonstrate that physics-informed adaptation can improve accuracy, stability, and deployment reliability for real-world mobile sensing systems.

Related papers

• Continual Test-Time Adaptation via Entropy Sensitivity-Guidance in Strict Online Setting [4.775158008378889]
  We introduce Sensitivity-Guided Erasing Adaptation (SEGA), a method for strict online continual TTA (CTTA) on corruption-style streams.<n>SEGA uses a small number of structured erasures to probe how predictive entropy changes as information is removed.<n>In experiments on ImageNet-C, CIFAR10/100-C, and corruption-generated aquaculture streams treated as controlled corruption-style proxies, SEGA yields consistent robustness and stability gains.
  arXiv  Detail & Related papers  (2026-08-30T17:30:51Z)
• TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs [83.78708832901194]
  Large video-language models (LVLMs) have shown remarkable performance on multimodal tasks like multimodal emotion recognition (ER) in the wild.<n>However, real-world deployment remains challenging: modalities may be missing or noisy at test time.<n>We propose a solution in which a frozen teacher guides an adaptive low-rank student via self-distillation.<n>Experiments on MELD, DFEW, and BAH under 0%-50% missing modalities show that this unified adaptation-restoration design consistently outperforms entropy-based adaptation, RAG, and perplexity-based generation.
  arXiv  Detail & Related papers  (2026-08-18T23:40:28Z)
• A Neural Network Based Teleoperation for Remote Controlled Vehicles [98.38733381483934]
  Direct teleoperation of vehicles faces critical technical bottlenecks.<n> communication latency and the operator's inability to physically perceive unmodeled environmental disturbances.<n>We propose a tailored unilateral teleoperation framework.
  arXiv  Detail & Related papers  (2026-08-11T01:51:08Z)
• PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective [52.693471818837395]
  We argue that PEFT should be assessed through the stability-plasticity dilemma.<n>We introduce PEFT-Arena, a benchmark that measures downstream performance and general capability retention.<n>Inspired by this, we present case studies of a post-hoc improvement with path-wise rewinding.
  arXiv  Detail & Related papers  (2026-05-27T17:59:51Z)
• Robust Cross-Domain WiFi Fall Detection via Physics-Driven Attention-Enhanced Transformers [64.35403680946182]
  Device-free fall detection utilizing WiFi Channel State Information (CSI) has emerged as a promising solution for elderly health monitoring.<n>Existing deep learning approaches suffer from severe performance degradation when deployed in unseen environments.<n>We propose a robust, domain-general framework featuring a novel Attention-Enhanced CNN-Transformer hybrid architecture.
  arXiv  Detail & Related papers  (2026-04-23T03:28:12Z)
• KD-EKF: Knowledge-Distilled Adaptive Covariance EKF for Robust UWB/PDR Indoor Localization [6.004649968619912]
  indoor localization provides centimeter-level accuracy and low latency.<n>Measurement reliability degrades severely under Non-Line-of-Sight conditions.<n>Inertial Measurement Unit (IMU)-based Pedestrian Dead Reckoning (PDR) provides infrastructure-free motion estimation.
  arXiv  Detail & Related papers  (2026-03-06T03:12:52Z)
• When Sensors Fail: Temporal Sequence Models for Robust PPO under Sensor Drift [64.37959940809633]
  We study robustness of Proximal Policy Optimization (PPO) under temporally persistent sensor failures.<n>We show Transformer-based sequence policies substantially outperform, RNN, and SSMs in robustness, maintaining high returns even when large fractions of sensors are unavailable.
  arXiv  Detail & Related papers  (2026-03-04T22:21:54Z)
• Physics-Guided Tiny-Mamba Transformer for Reliability-Aware Early Fault Warning [2.491980790083337]
  We propose the Physics-Guided Tiny-Mamba Transformer (PG-TMT), a compact tri-branch encoder tailored for online condition monitoring.<n>A depthwise-separable convolutional stem captures micro-transients, a Tiny-Mamba state-space branch models near-linear long-range dynamics, and a lightweight local Transformer encodes cross-channel resonances.<n>PG-TMT delivers, interpretable, and deployment-ready early warnings for reliability-centric prognostics and health management.
  arXiv  Detail & Related papers  (2026-01-29T05:46:12Z)
• Calibration-Free EEG-based Driver Drowsiness Detection with Online Test-Time Adaptation [43.83587667787693]
  Drowsy driving is a growing cause of traffic accidents, prompting recent exploration of electroencephalography (EEG)-based drowsiness detection systems.<n>In particular, the inter-subject variability of EEG signals leads to a domain shift problem, which makes it challenging to generalize drowsiness detection models to unseen target subjects.<n>We propose a novel driver drowsiness detection framework that leverages online test-time adaptation methods to dynamically adjust to target subject distributions.
  arXiv  Detail & Related papers  (2025-11-27T02:27:10Z)
• ICD-Net: Inertial Covariance Displacement Network for Drone Visual-Inertial SLAM [5.5217350574838875]
  We present ICD-Net, a novel framework that enhances visual-inertial SLAM performance.<n>Our approach significantly improved trajectory estimation accuracy compared to standard VINS-Fusion.<n>Our method shows that neural network enhancement can effectively address multiple sources of SLAM degradation.
  arXiv  Detail & Related papers  (2025-11-13T11:25:02Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints [51.83081671798784]
  Diffusion Transformers (DiT) have emerged as a powerful architecture for image and video generation, offering superior quality and scalability.<n>DiT's practical application suffers from inherent dynamic feature instability, leading to error amplification during cached inference.<n>We propose Skip-DiT, an image and video generative DiT variant enhanced with Long-Skip-Connections (LSCs) - the key efficiency component in U-Nets.
  arXiv  Detail & Related papers  (2024-11-26T17:28:10Z)
• Freezing of Gait Detection Using Gramian Angular Fields and Federated Learning from Wearable Sensors [6.369424231505372]
  Freezing of gait (FOG) is a debilitating symptom of Parkinson's disease.<n>We present FOGSense, a real-world deployable FOG detection system using only a single sensor.
  arXiv  Detail & Related papers  (2024-11-18T17:43:43Z)
• Real-time Object Detection for Streaming Perception [84.2559631820007]
  Streaming perception is proposed to jointly evaluate the latency and accuracy into a single metric for video online perception. We build a simple and effective framework for streaming perception. Our method achieves competitive performance on Argoverse-HD dataset and improves the AP by 4.9% compared to the strong baseline.
  arXiv  Detail & Related papers  (2022-03-23T11:33:27Z)
• TLIO: Tight Learned Inertial Odometry [43.17991168599939]
  We propose a tightly-coupled Extended Kalman Filter framework for IMU-only state estimation. We show that our network, trained with pedestrian data from a headset, can produce statistically consistent measurement and uncertainty.
  arXiv  Detail & Related papers  (2020-07-06T03:13:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.