In few-shot unsupervised domain adaptation (FS-UDA), most existing methods followed the few-shot learning (FSL) methods to leverage the low-level local features (learned from conventional convolutional models, e.g., ResNet) for classification. However, the goal of FS-UDA and FSL are relevant yet distinct, since FS-UDA aims to classify the samples in target domain rather than source domain. We found that the local features are insufficient to FS-UDA, which could introduce noise or bias against classification, and not be used to effectively align the domains. To address the above issues, we aim to refine the local features to be more discriminative and relevant to classification. Thus, we propose a novel task-specific semantic feature learning method (TSECS) for FS-UDA. TSECS learns high-level semantic features for image-to-class similarity measurement. Based on the high-level features, we design a cross-domain self-training strategy to leverage the few labeled samples in source domain to build the classifier in target domain. In addition, we minimize the KL divergence of the high-level feature distributions between source and target domains to shorten the distance of the samples between the two domains. Extensive experiments on DomainNet show that the proposed method significantly outperforms SOTA methods in FS-UDA by a large margin (i.e., ~10%).

Due to the conventional extended state observer (ESO) has the low-pass characteristic, the phase shift of the back electromotive force (back EMF) estimated by ESO is caused. To improve the estimation accuracy of back EMF, a modified frequency-adaptive extended state observer (FAESO) is proposed. It uses the second-order generalized integrator (SOGI) to instead of the pure integrator, which makes FAESO has the band-pass characteristic and the phase shift angle at central frequency is zero. Hence, the accurate back EMF without phase shift can be estimated by the FAESO. Considering the phase-locked loop (PLL) cannot extract the rotor speed and position effectively in dynamic process, a motion equation based extended state observer (LESO) is proposed. The load torque is taken as extended state and estimated by LESO. The extraction accuracy and rapidity of rotor position and speed are effectively improved in this way. Finally, a 750W PMSM is used as the control object, and the effectiveness of the proposed method is proved by comparing with the conventional method.

Unsupervised domain adaptation (UDA) has raised a lot of interests in recent years. However, current UDA methods are still not capable enough in dealing with two issues: 1) the scarcity of labeled data in source domain and 2) the need of a general model that can quickly adapt to solve new UDA tasks. To address this situation, we investigate available but rarely-studied setting called few-shot unsupervised domain adaptation (FS-UDA), in which the data of source domain is few-shot per category and the data of target domain remains unlabeled. To realize effective adaptation for FS-UDA tasks in the same source and target domains, we propose a novel meta learning method namely meta-FUDA, which leverages meta learning to perform task-level transfer and domain-level transfer jointly. Extensive experiments demonstrate the promising performance of our method on multiple benchmark data sets.

This paper investigates a valuable setting called few-shot unsupervised domain adaptation (FS-UDA), which has not been sufficiently studied in the literature. In this setting, the source domain data are labelled, but with few-shot per category, while the target domain data are unlabelled. To address the FS-UDA setting, we develop a general UDA model to solve the following two key issues: the few-shot labeled data per category and the domain adaptation between support and query sets. Our model is general in that once trained it will be able to be applied to various FS-UDA tasks from the same source and target domains. Inspired by the recent local descriptor based few-shot learning (FSL), our general UDA model is fully built upon local descriptors (LDs) for image classification and domain adaptation. By proposing a novel concept called similarity patterns (SPs), our model not only effectively considers the spatial relationship of LDs that was ignored in previous FSL methods, but also makes the learned image similarity better serve the required domain alignment. Specifically, we propose a novel IMage-to-class sparse Similarity Encoding (IMSE) method. It learns SPs to extract the local discriminative information for classification and meanwhile aligns the covariance matrix of the SPs for domain adaptation. Also, domain adversarial training and multi-scale local feature matching are performed upon LDs. Extensive experiments conducted on a multi-domain benchmark dataset DomainNet demonstrates the state-of-the-art performance of our IMSE for the novel setting of FS-UDA. In addition, for FSL, our IMSE can also show better performance than most of recent FSL methods on miniImageNet.