# Semantic-Discriminative Mixup for Generalizable Sensor-based Cross-domain Activity Recognition

arXiv: https://arxiv.org/abs/2206.06629 · HTML: https://mlsanity.com/paper/2206.06629/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 14 Jun 2022.

## Builds on (most cited first, 26 of 26)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)
- [A Survey of Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1812.02849/) (2018)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- [A Fourier-based Framework for Domain Generalization](https://mlsanity.com/paper/2105.11120/) (2021)
- [Gradient Matching for Domain Generalization](https://mlsanity.com/paper/2104.09937/) (2021)
- [Adversarial Domain Adaptation with Domain Mixup](https://mlsanity.com/paper/1912.01805/) (2019)
- [Deep Learning for Sensor-based Activity Recognition: A Survey](https://mlsanity.com/paper/1707.03502/) (2017)
- [Learning explanations that are hard to vary](https://mlsanity.com/paper/2009.00329/) (2020)
- [DIVA: Domain Invariant Variational Autoencoders](https://mlsanity.com/paper/1905.10427/) (2019)
- [Large Margin Deep Networks for Classification](https://mlsanity.com/paper/1803.05598/) (2018)
- [Heterogeneous Domain Generalization via Domain Mixup](https://mlsanity.com/paper/2009.05448/) (2020)
- [Dual Mixup Regularized Learning for Adversarial Domain Adaptation](https://mlsanity.com/paper/2007.03141/) (2020)
- [Best sources forward: domain generalization through source-specific nets](https://mlsanity.com/paper/1806.05810/) (2018)
- [Correlation-aware Adversarial Domain Adaptation and Generalization](https://mlsanity.com/paper/1911.12983/) (2019)
- [A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation](https://mlsanity.com/paper/1809.01361/) (2018)
- [UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones](https://mlsanity.com/paper/1611.07688/) (2016)
- [Meta-Learning for Domain Generalization in Semantic Parsing](https://mlsanity.com/paper/2010.11988/) (2020)
- [Stratified Transfer Learning for Cross-domain Activity Recognition](https://mlsanity.com/paper/1801.00820/) (2017)
- [Deep Transfer Learning for Cross-domain Activity Recognition](https://mlsanity.com/paper/1807.07963/) (2018)
- [Cross-domain Activity Recognition via Substructural Optimal Transport](https://mlsanity.com/paper/2102.03353/) (2021)
- [Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization](https://mlsanity.com/paper/2002.05660/) (2020)

## Built on by (most cited first, 29 of 29)

- [FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learning](https://mlsanity.com/paper/2302.13485/) (2023)
- [MetaFed: Federated Learning among Federations with Cyclic Knowledge Distillation for Personalized Healthcare](https://mlsanity.com/paper/2206.08516/) (2022)
- [Domain-invariant Feature Exploration for Domain Generalization](https://mlsanity.com/paper/2207.12020/) (2022)
- [UniMTS: Unified Pre-training for Motion Time Series](https://mlsanity.com/paper/2410.19818/) (2024)
- [DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization](https://mlsanity.com/paper/2308.02282/) (2023)
- [Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition](https://mlsanity.com/paper/2310.18562/) (2023)
- [Transfer Learning in Human Activity Recognition: A Survey](https://mlsanity.com/paper/2401.10185/) (2024)
- [Generalizable Low-Resource Activity Recognition with Diverse and Discriminative Representation Learning](https://mlsanity.com/paper/2306.04641/) (2023)
- [A Survey on Multimodal Wearable Sensor-based Human Action Recognition](https://mlsanity.com/paper/2404.15349/) (2024)
- [Cross Contrasting Feature Perturbation for Domain Generalization](https://mlsanity.com/paper/2307.12502/) (2023)
- [Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup](https://mlsanity.com/paper/2305.16817/) (2023)
- [FIXED: Frustratingly Easy Domain Generalization with Mixup](https://mlsanity.com/paper/2211.05228/) (2022)
- [Large Language Model-Guided Semantic Alignment for Human Activity Recognition](https://mlsanity.com/paper/2410.00003/) (2024)
- [Towards Generalizable Human Activity Recognition: A Survey](https://mlsanity.com/paper/2508.12213/) (2025)
- [MAC-Gaze: Motion-Aware Continual Calibration for Mobile Gaze Tracking](https://mlsanity.com/paper/2505.22769/) (2025)
- [HAROOD: A Benchmark for Out-of-distribution Generalization in Sensor-based Human Activity Recognition](https://mlsanity.com/paper/2512.10807/) (2025)
- [Infinite Class Mixup](https://mlsanity.com/paper/2305.10293/) (2023)
- [FedAli: Personalized Federated Learning Alignment with Prototype Layers for Generalized Mobile Services](https://mlsanity.com/paper/2411.10595/) (2024)
- [HAR-DoReMi: Optimizing Data Mixture for Self-Supervised Human Activity Recognition Across Heterogeneous IMU Datasets](https://mlsanity.com/paper/2503.13542/) (2025)
- [BenchHAR: Benchmarking Self-Supervised Learning for Generalizable Sensor-based Activity Recognition](https://mlsanity.com/paper/2605.08296/) (2026)
- [CODA: A Continuous Online Evolve Framework for Deploying HAR Sensing Systems](https://mlsanity.com/paper/2403.14922/) (2024)
- [SelfReplay: Adapting Self-Supervised Sensory Models via Adaptive Meta-Task Replay](https://mlsanity.com/paper/2404.15305/) (2024)
- [Human Heterogeneity Invariant Stress Sensing](https://mlsanity.com/paper/2506.02256/) (2025)
- [Wearable-based behaviour interpolation for semi-supervised human activity recognition](https://mlsanity.com/paper/2405.15962/) (2024)
- [GenHAR: Generalizing Cross-domain Human Activity Recognition for Last-mile Delivery](https://mlsanity.com/paper/2605.22086/) (2026)
- [Assessing Distribution Shift in Human Activity Recognition for Domain Generalization](https://mlsanity.com/paper/2606.24781/) (2026)
- [VSMP-IMU: Video-Grounded Semantic Motion Programs for Sensor-Aware Synthetic IMU Generation](https://mlsanity.com/paper/2608.05782/) (2026)
- [Domain Generalization for Smartphone-Based Human Activity Recognition: A Systematic Analysis of Components and Interactions](https://mlsanity.com/paper/2609.14863/) (2026)
- [Characterizing the Performance Gap in Human Activity Recognition for Older Adults](https://mlsanity.com/paper/2610.02711/) (2026)

## Abstract (arXiv)

It is expensive and time-consuming to collect sufficient labeled data to build human activity recognition (HAR) models. Training on existing data often makes the model biased towards the distribution of the training data, thus the model might perform terribly on test data with different distributions. Although existing efforts on transfer learning and domain adaptation try to solve the above problem, they still need access to unlabeled data on the target domain, which may not be possible in real scenarios. Few works pay attention to training a model that can generalize well to unseen target domains for HAR. In this paper, we propose a novel method called Semantic-Discriminative Mixup (SDMix) for generalizable cross-domain HAR. Firstly, we introduce semantic-aware Mixup that considers the activity semantic ranges to overcome the semantic inconsistency brought by domain differences. Secondly, we introduce the large margin loss to enhance the discrimination of Mixup to prevent misclassification brought by noisy virtual labels. Comprehensive generalization experiments on five public datasets demonstrate that our SDMix substantially outperforms the state-of-the-art approaches with 6% average accuracy improvement on cross-person, cross-dataset, and cross-position HAR.