Search

This paper advances the theory and practice of Domain Generalization (DG) in machine learning. We consider the typical DG setting where the hypothesis is composed of a representation mapping followed by a labeling function. Within this setting, the majority of popular DG methods aim to jointly learn the representation and the labeling functions by minimizing a well-known upper bound for the classification risk in the unseen domain. In practice, however, methods based on this theoretical upper bound ignore a term that cannot be directly optimized due to its dual dependence on both the representation mapping and the unknown optimal labeling function in the unseen domain. To bridge this gap between theory and practice, we introduce a new upper bound that is free of terms having such dual dependence, resulting in a fully optimizable risk upper bound for the unseen domain. Our derivation leverages classical and recent transport inequalities that link optimal transport metrics with information-theoretic measures. Compared to previous bounds, our bound introduces two new terms: (i) the Wasserstein-2 barycenter term that aligns distributions between domains, and (ii) the reconstruction loss term that assesses the quality of representation in reconstructing the original data. Based on this new upper bound, we propose a novel DG algorithm named Wasserstein Barycenter Auto-Encoder (WBAE) that simultaneously minimizes the classification loss, the barycenter loss, and the reconstruction loss. Numerical results demonstrate that the proposed method outperforms current state-of-the-art DG algorithms on several datasets.

3D face recognition (FR) has become increasingly widespread due to the illumination invariance and pose robustness of 3D face data. Most existing 3D FR methods can only achieve excellent performance on complete and smooth faces. However, low-quality 3D FR with missing facial features still suffers from insufficient discriminative feature extraction for visible face regions. In this paper, we propose a dual-stream multi-scale fusion network (DSNet) for low-quality 3D FR. First, in the first stream, we design a new multi-scale local and global feature fusion network, which consists of an enhanced shallow feature extraction module, an enhanced deep feature extraction module, and a layered multi-scale feature correlation fusion module, aiming to obtain more discriminative details and category information of the facial visible region, reducing the interference of similar features and the redundancy of the same features. Second, we also introduced a capsule network as the second stream to enhance the expression of 3D facial spatial position information, thereby further improving the performance of low-quality 3D FR with missing facial features. We conduct extensive experiments on low-quality datasets (Lock3DFace, KinectFaceDB, and IIIT-D) and cross-quality datasets synthesized by Bosphorus. These results show that our proposed DSNet can achieve state-of-the-art recognition performance and exhibit excellent performance on low-quality 3D faces with missing facial features.

Abstract Sensor platforms that exploit the fibrous textile threads as substrates offer great promise since they can be directly sewn, woven or stitched on to any clothing. They can also be placed directly in intimate contact with the skin. In this work, we present a thread-based sensing platform in the form of a multiplexed sensing patch for continuous simultaneous on-skin monitoring of sweat. The patch performs real-time, on-body measurements of important biomarkers present in sweat such as electrolytes (sodium and ammonium ions), metabolites (lactate) and acidity (pH). Flexible threads coated with conductive inks were used as sensing electrodes. Selective potentiometric detection of electrolytes and pH was made possible through ion-selective membrane deposition and pH-sensitive polyaniline coating on threads, respectively. An amperometric enzymatic sensing scheme with lactate oxidase was used for the detection of lactate. An array of the thread sensors is integrated onto a patch with connectivity to a miniaturized circuit module containing a potentiostat, microprocessor and wireless circuitry for wireless smartphone readout. Extensive in vitro validation and an in vivo human pilot study involving a maximal exertion test show the promise of this platform for real-time physiological monitoring of human performance/fitness under stress, as well as diagnostic monitoring through sweat analysis.