# Conservative Subject Invariant EMG-based Gesture Recognition

arXiv: https://arxiv.org/abs/2607.03783 · HTML: https://mlsanity.com/paper/2607.03783/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 31 references that are in the map.
- First posted on arXiv 4 Jul 2026.

## Builds on (most cited first, 5 of 5)

- [Regularisation of Neural Networks by Enforcing Lipschitz Continuity](https://mlsanity.com/paper/1804.04368/) (2018)
- [Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks](https://mlsanity.com/paper/1802.04034/) (2018)
- [Interpreting Deep Learning Features for Myoelectric Control: A Comparison with Handcrafted Features](https://mlsanity.com/paper/1912.00283/) (2019)
- [EMGBench: Benchmarking Out-of-Distribution Generalization and Adaptation for Electromyography](https://mlsanity.com/paper/2410.23625/) (2024)
- [Performance Optimization of Surface Electromyography (sEMG) based Biometric Sensing System for both Verification and Identification](https://mlsanity.com/paper/2103.06015/) (2021)

## Abstract (arXiv)

Cross-subject generalization remains a fundamental challenge in surface electromyography (sEMG)-based gesture recognition. Although deep learning methods have improved within-subject performance, they often rely on subject-specific data and struggle to balance invariance and discriminability. In this work, we propose a conservative multi-objective learning framework for subject-invariant sEMG gesture recognition. The proposed model adopts a multi-head architecture that jointly optimizes gesture classification, adversarial subject confusion through gradient reversal, and triplet-based metric learning to encourage discriminative and subject-invariant representations. To improve optimization stability, a Lipschitz-inspired adaptive weighting mechanism is introduced to dynamically balance the auxiliary objectives according to their relative magnitudes during training. The proposed method is evaluated on two benchmark datasets: UCI EMG (36 subjects, 6 gestures) and NinaPro DB5 (10 subjects, 10 gestures). On the UCI EMG dataset, the method achieves 84.48% accuracy compared to 78.2% reported by state-of-the-art methods. On NinaPro DB5, it achieves 61.44% accuracy versus 41.30%, corresponding to a 49% relative improvement. In addition, the proposed framework reduces cross-subject prediction variance and produces more structured latent representations. These results indicate that jointly enforcing invariance and discriminability through adaptive multi-objective optimization leads to more stable training and improved cross-subject generalization in sEMG-based gesture recognition systems.