Deep learning methods often struggle with the domain shift problem, leading to poor generalization on out-of-domain (OOD) data. To address the problem, domain generalization (DG) has been proposed to leverage the source domains to train a model that can generalize to OOD data. Existing domain generalization methods primarily focus on learning domain invariance, but they fail to ensure proximity among samples within the same category when domains are aligned for domain-invariant learning. Consequently, their generalization performance remains suboptimal. In this paper, we propose a novel approach to address this issue by iteratively approximating the category domain-invariant distribution from all domains. Our method involves an iterative loop where we initially estimate the domain-invariant distribution for each category by averaging the statistical characteristics across all domains. Then the adversarial perturbation alignment is adopted to keep each sample close to its corresponding category domain-invariant distribution. With the iterative loop, the deep network is optimized for robust domain invariance learning. Extensive experiments demonstrate that our proposed method consistently outperforms state-of-the-art approaches across various scenarios.

Multi-source domain adaptation (MSDA) aims to transfer knowledge from multiple source domains to the unlabeled target domain. In this paper, we propose a cycle self-refinement domain adaptation method, which progressively attempts to learn the dominant transferable knowledge in each source domain in a cycle manner. Specifically, several source-specific networks and a domain-ensemble network are adopted in the proposed method. The source-specific networks are adopted to provide the dominant transferable knowledge in each source domain for instance-level ensemble on predictions of the samples in target domain. Then these samples with high-confidence ensemble predictions are adopted to refine the domain-ensemble network. Meanwhile, to guide each source-specific network to learn more dominant transferable knowledge, we force the features of the target domain from the domain-ensemble network and the features of each source domain from the corresponding source-specific network to be aligned with their predictions from the corresponding networks. Thus the adaptation ability of source-specific networks and the domain-ensemble network can be improved progressively. Extensive experiments on Office-31, Office-Home and DomainNet show that the proposed method outperforms the state-of-the-art methods for most tasks.

Long-term incorrect sitting undoubtedly will damage physical health. Recognizing bad sitting posture has been of particular interest recently due to the prevailing Internet of Healthcare Things (IoHT). While various sitting posture recognition systems based on wearable devices and cameras are designed, they expose two obvious weaknesses. First, the sensors attached to the body will cause inconvenience to users, and using a camera requires high energy consumption and faces the risk of user privacy leakage. Second, most of these systems require massive training samples to build models, and the recognition performance of certain models on new user data with significant sample distribution differences remains poor. In this work, we propose SmartSit, the first-ever robust sitting posture recognition system with smartphone acoustic sensing. We start by designing a signal detection algorithm to determine the boundary of the sitting posture signal through a series of signal transformation methods. Then we construct the sitting posture recognition module MG-Reptile by modifying the meta-learning method by combining the Distributed Measurement Strategy (DMS) and Generative Adversarial Network (GAN). We show that the designed system is immune to the low generalization performance with only a few training samples. The observed testing results further validate the effectiveness and robustness of SmartSit.

Due to the lack of labeled data in many real-world applications, unsupervised domain adaptation has attracted a great deal of attention in the machine learning community through its use of labeled data from source domains. However, how to make full use of the discriminative information from different sources remains a challenge due to various domain gaps. In this article, we propose a domain complementary adaptation method by leveraging the diversity between sources and the discriminability of each source with contrastive learning. In the proposed method, we adopt several branch networks, denoted as domain branch networks, to learn different views of discriminative domain-invariant features from each source. Moreover, an ensemble classification network trained with domain-invariant features from all domain branch networks is adopted to guide the domain branch networks in providing diverse knowledge. We design a domain mutual contrastive loss by forcing the domain branch networks to be different from one another and be consistent with the ensemble classification network to learn diverse domain-invariant features. To further improve the discriminability of domain branch networks, a domain structure-oriented contrastive loss is proposed to learn the discriminative intrinsic neighborhood structure across each source and target domain. Extensive experiments on the Office-31, Office-Home and DomainNet datasets show that the proposed method outperforms state-of-the-art methods.

Multi-source domain adaptation has attracted great attention in machine learning community. Most of these methods focus on weighting the predictions produced by the adaptation networks of different domains. Thus the domain shifts between certain of domains and target domain are not effectively relieved, resulting in that these domains are not fully exploited and even may have a negative influence on multi-source domain adaptation task. To address such challenge, we propose a multi-source domain adaptation method to gradually improve the adaptation ability of each source domain by producing more high-confident pseudo-labels with self-paced learning for conditional distribution alignment. The proposed method first trains several separate domain branch networks with single domains and an ensemble branch network with all domains. Then we obtain some high-confident pseudo-labels with the branch networks and learn the branch specific pseudo-labels with self-paced learning. Each branch network reduces the domain gap by aligning the conditional distribution with its branch specific pseudo-labels and the pseudo-labels provided by all branch networks. Experiments on Office31, Office-Home and DomainNet show that the proposed method outperforms the state-of-the-art methods.