Transfer learning(TL)utilizes data or knowledge from one or more source domains to facilitate learning in a target *** is particularly useful when the target domain has very few or no labeled data,due to annotation ex...
详细信息
Transfer learning(TL)utilizes data or knowledge from one or more source domains to facilitate learning in a target *** is particularly useful when the target domain has very few or no labeled data,due to annotation expense,privacy concerns,***,the effectiveness of TL is not always *** transfer(NT),i.e.,leveraging source domain data/knowledge undesirably reduces learning performance in the target domain,and has been a long-standing and challenging problem in *** approaches have been proposed in the literature to address this ***,there does not exist a systematic *** paper fills this gap,by first introducing the definition of NT and its causes,and reviewing over fifty representative approaches for overcoming NT,which fall into three categories:domain similarity estimation,safe transfer,and NT *** areas,including computer vision,bioinformatics,natural language processing,recommender systems,and robotics,that use NT mitigation strategies to facilitate positive transfers,are also ***,we give guidelines on NT task construction and baseline algorithms,benchmark existing TL and NT mitigation approaches on three NT-specific datasets,and point out challenges and future research *** ensure reproducibility,our code is publicized at https://***/chamwen/NT-Benchmark.
Integrated sensing and communication (ISAC) technology is at the forefront of next-generation communication, enhancing applications from intel-ligent transportation to unmanned aerial vehicle surveillance and healthca...
详细信息
This article studies the consensus problem for multiagent systems with transmission constraints. A novel model of multiagent systems is proposed where the information transmissions between agents are disturbed by irre...
详细信息
controlling networks aims to study the models, structures,and related dynamics of complex networks. The primary problem of controlling networks is to determine whether they are controllable. Nowadays, controllability ...
controlling networks aims to study the models, structures,and related dynamics of complex networks. The primary problem of controlling networks is to determine whether they are controllable. Nowadays, controllability has been widely studied and applied to system engineering and control theory, power systems, aerospace, and quantum systems. Various classical criteria include the Gram matrix criterion, Kalman rank criterion, and PBH test.
Electroencephalogram (EEG)-based seizure sub-type classification enhances clinical diagnosis efficiency. Source-free semi-supervised domain adaptation (SF-SSDA), which transfers a pre-trained model to a new dataset wi...
详细信息
Ensemble learning aggregates outputs from multiple base learners for better performance. Bootstrap aggregating (bagging) and boosting are two popular such approaches. They are suitable for integrating unstable base le...
详细信息
Semisupervised domain adaptation (SSDA) aims at training a high-performance model for a target domain using few labeled target data, many unlabeled target data, and plenty of auxiliary data from a source domain. Previ...
详细信息
Dear Editor, This letter investigates the prescribed-time stabilization of linear singularly perturbed systems. Due to the numerical issues caused by the small perturbation parameter, the off-the-shelf control design ...
详细信息
Dear Editor, This letter investigates the prescribed-time stabilization of linear singularly perturbed systems. Due to the numerical issues caused by the small perturbation parameter, the off-the-shelf control design techniques for the prescribed-time stabilization of regular linear systems are typically not suitable here. To solve the problem, the decoupling transformation techniques for time-varying singularly perturbed systems are combined with linear time-varying high gain feedback design techniques.
Portrait matting is a challenging computer vision task that aims to estimate the per-pixel opacity of the foreground human regions. To produce high-quality alpha mattes, the majority of available methods employ a user...
详细信息
This study introduces an innovative approach for gesture recognition in smart wearable devices using a deep domain adaptation model, focusing on the challenges posed by heterogeneous user environments and the need for...
详细信息
暂无评论