In this paper we propose a new approach to motion-compensated ltering of image sequences that contain time-varying illumination. There are two contributions in this paper. First, we propose a new method for the estimation of dense 2-D motion that is robust to time-varying illumination often present in images. We deene the structural model that is based on the assumption of intensity gradient co...

Detecting out-of-distribution (OOD) samples is crucial to the safe deployment of a classifier in real world. However, deep neural networks are known be overconfident for abnormal data. Existing works directly design score function by mining inconsistency from in-distribution (ID) and OOD. In this paper, we further complement with reconstruction error, based on assumption that an autoencoder tra...

Abstract Label noise is an important data quality issue that negatively impacts machine learning algorithms. For example, label has been shown to increase the number of instances required train effective predictive models. It also model complexity and decrease interpretability. In addition, can cause classification results a learner be poor. this paper, we detect with three unsupervised learner...