Semantic-Discriminative Mixup for Generalizable Sensor-based Cross-domain Activity Recognition
This addresses the challenge of costly data collection and model bias in sensor-based activity recognition for real-world applications, though it is incremental as it builds on existing mixup techniques.
The paper tackles the problem of generalizing human activity recognition models to unseen target domains without requiring target domain data, proposing Semantic-Discriminative Mixup (SDMix) which achieves a 6% average accuracy improvement over state-of-the-art methods in cross-domain experiments.
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.