{"ID":5937925,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T09:09:15.243812604Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.03783","arxiv_id":"2607.03783","title":"Conservative Subject Invariant EMG-based Gesture Recognition","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2607.03783","url_pdf":"https://arxiv.org/pdf/2607.03783v1","authors":"[\"Hamed Rafiei\",\"Ali Mousavi\"]","published":"2026-07-04T09:14:11Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}