Unsupervised Domain Adaptive (UDA) object re-identification (Re-ID) aims at adapting a model trained on labeled source domain to an unlabeled target domain. State-of-the-art Re-ID approaches adopt clustering algorithms generate pseudo-labels for the However, inevitable label noise caused by procedure significantly degrades discriminative power of model. To address this problem, we propose uncer...

The one-shot person Re-ID scenario faces two kinds of uncertainties when constructing the prediction model from X to Y. first is uncertainty, which captures noise parameters in DNNs due a lack training data. second data can be divided into subtypes: image noise, where severe occlusion and complex background contain irrelevant information about identity; label mislabeling affects visual appearan...

This paper presents a new controller validation method for linear multivariable time-invariant models. Classical prediction error system identification methods deliver uncertainty regions which are nonstandard in the robust control literature. Our controller validation criterion computes an upper bound for the worst case performance, measured in terms of the H∞-norm of a weighted closed loop tr...

Abstract. Tie-rods are simple structural elements that have been commonly used throughout the centuries to improve stability of old masonry buildings. Measuring dynamic vibrations such can give important information on performance variation with time if proper system models be calibrated taking into account all relevant sources uncertainties. This paper poses and solves inverse problem quantify...