# Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition

arXiv: https://arxiv.org/abs/2310.18562 · HTML: https://mlsanity.com/paper/2310.18562/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 58 references that are in the map.
- First posted on arXiv 28 Oct 2023.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Vision Transformers are Robust Learners](https://mlsanity.com/paper/2105.07581/) (2021)
- [Deep Learning for Sensor-based Activity Recognition: A Survey](https://mlsanity.com/paper/1707.03502/) (2017)
- [TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation](https://mlsanity.com/paper/2302.05155/) (2023)
- [DELTA: degradation-free fully test-time adaptation](https://mlsanity.com/paper/2301.13018/) (2023)
- [Revisiting Locally Supervised Learning: an Alternative to End-to-end Training](https://mlsanity.com/paper/2101.10832/) (2021)
- [Adaptive Methods for Real-World Domain Generalization](https://mlsanity.com/paper/2103.15796/) (2021)
- [Test-Time Adaptation via Self-Training with Nearest Neighbor Information](https://mlsanity.com/paper/2207.10792/) (2022)
- [UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones](https://mlsanity.com/paper/1611.07688/) (2016)
- [Test-time Batch Statistics Calibration for Covariate Shift](https://mlsanity.com/paper/2110.04065/) (2021)
- [AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation](https://mlsanity.com/paper/2304.12566/) (2023)
- [MixNorm: Test-Time Adaptation Through Online Normalization Estimation](https://mlsanity.com/paper/2110.11478/) (2021)
- [Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering](https://mlsanity.com/paper/2206.02721/) (2022)
- [Semantic-Discriminative Mixup for Generalizable Sensor-based Cross-domain Activity Recognition](https://mlsanity.com/paper/2206.06629/) (2022)
- [Domain Generalization for Activity Recognition via Adaptive Feature Fusion](https://mlsanity.com/paper/2207.11221/) (2022)
- [Uncovering Adversarial Risks of Test-Time Adaptation](https://mlsanity.com/paper/2301.12576/) (2023)
- [Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognition](https://mlsanity.com/paper/2202.07260/) (2022)

## Built on by (most cited first, 18 of 18)

- [NEO: No-Optimization Test-Time Adaptation through Latent Re-Centering](https://mlsanity.com/paper/2510.05635/) (2025)
- [Towards Generalizable Human Activity Recognition: A Survey](https://mlsanity.com/paper/2508.12213/) (2025)
- [Generalizable Sensor-Based Activity Recognition via Categorical Concept Invariant Learning](https://mlsanity.com/paper/2412.13594/) (2024)
- [BoTTA: Benchmarking on-device Test Time Adaptation](https://mlsanity.com/paper/2504.10149/) (2025)
- [On-device Learning of EEGNet-based Network For Wearable Motor Imagery Brain-Computer Interface](https://mlsanity.com/paper/2409.00083/) (2024)
- [Deconfounding Causal Inference through Two-Branch Framework with Early-Forking for Sensor-Based Cross-Domain Activity Recognition](https://mlsanity.com/paper/2507.03898/) (2025)
- [Temporal Structure Matters for Efficient Test-Time Adaptation in Wearable Human Activity Recognition](https://mlsanity.com/paper/2605.04617/) (2026)
- [BenchHAR: Benchmarking Self-Supervised Learning for Generalizable Sensor-based Activity Recognition](https://mlsanity.com/paper/2605.08296/) (2026)
- [AdaShadow: Responsive Test-time Model Adaptation in Non-stationary Mobile Environments](https://mlsanity.com/paper/2410.08256/) (2024)
- [Chorus: Harmonizing Context and Sensing Signals for Data-Free Model Customization in IoT](https://mlsanity.com/paper/2512.15206/) (2025)
- [Domain-Adversarial Anatomical Graph Networks for Cross-User Human Activity Recognition](https://mlsanity.com/paper/2505.06301/) (2025)
- [Graph-Based Adversarial Domain Generalization with Anatomical Correlation Knowledge for Cross-User Human Activity Recognition](https://mlsanity.com/paper/2506.01962/) (2025)
- [Collaborative Temporal Feature Generation via Critic-Free Reinforcement Learning for Cross-User Sensor-Based Activity Recognition](https://mlsanity.com/paper/2603.16043/) (2026)
- [EdgeHAR: An Edge-Native Compact Sensor Foundation Model for Human Activity Recognition](https://mlsanity.com/paper/2609.14498/) (2026)
- [When Adaptation Hurts: Split Sensitivity and Person-Level Negative Transfer in Federated Wearable Onboarding](https://mlsanity.com/paper/2609.27819/) (2026)
- [LiteEMG-FM: An Efficient and Deployable Foundation Model for Robust EMG Sensing](https://mlsanity.com/paper/2610.02497/) (2026)
- [Characterizing the Performance Gap in Human Activity Recognition for Older Adults](https://mlsanity.com/paper/2610.02711/) (2026)
- [What Egocentric Video Embeddings Encode and How to Combine Them with Inertial Sensors for Human Activity Recognition](https://mlsanity.com/paper/2610.12926/) (2026)

## Abstract (arXiv)

Human Activity Recognition (HAR) models often suffer from performance degradation in real-world applications due to distribution shifts in activity patterns across individuals. Test-Time Adaptation (TTA) is an emerging learning paradigm that aims to utilize the test stream to adjust predictions in real-time inference, which has not been explored in HAR before. However, the high computational cost of optimization-based TTA algorithms makes it intractable to run on resource-constrained edge devices. In this paper, we propose an Optimization-Free Test-Time Adaptation (OFTTA) framework for sensor-based HAR. OFTTA adjusts the feature extractor and linear classifier simultaneously in an optimization-free manner. For the feature extractor, we propose Exponential DecayTest-time Normalization (EDTN) to replace the conventional batch normalization (CBN) layers. EDTN combines CBN and Test-time batch Normalization (TBN) to extract reliable features against domain shifts with TBN's influence decreasing exponentially in deeper layers. For the classifier, we adjust the prediction by computing the distance between the feature and the prototype, which is calculated by a maintained support set. In addition, the update of the support set is based on the pseudo label, which can benefit from reliable features extracted by EDTN. Extensive experiments on three public cross-person HAR datasets and two different TTA settings demonstrate that OFTTA outperforms the state-of-the-art TTA approaches in both classification performance and computational efficiency. Finally, we verify the superiority of our proposed OFTTA on edge devices, indicating possible deployment in real applications. Our code is available at https://github.com/Claydon-Wang/OFTTA.