Integrating Parametric and Non-Parametric Models For Scene Labeling
We adopt Convolutional Neural Networks (CNN) as our parametric model to learn discriminative features and classifiers for local patch classification. As visually similar pixels are indistinguishable from local context, we alleviate such ambiguity by putting a global scene constraint. We estimate the global potential in a non-parametric framework. Furthermore, a large margin based CNN metric learning method is proposed for better global potential estimation. The final pixel class prediction is performed by integrating local and global beliefs. Even without any post-processing, we achieve state-of-the-art on SiftFlow and competitive results on Stanford Background benchmark.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationMetric LearningScene LabelingSimilar Papers 제목 키워드 기반
Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detection
Multiple-instance learning (MIL) provides an effective way to tackle the video anomaly detection problem by modeling it as a weakly supervised problem as the labels are usually only available at the video level while mis…
Anomaly DetectionMultiple Instance LearningVideo Anomaly DetectionWeakly-supervised Video Anomaly DetectionScene Parsing with Integration of Parametric and Non-parametric Models
We adopt Convolutional Neural Networks (CNNs) to be our parametric model to learn discriminative features and classifiers for local patch classification. Based on the occurrence frequency distribution of classes, an ense…
Metric LearningScene ParsingJoint M-Best-Diverse Labelings as a Parametric Submodular Minimization
We consider the problem of jointly inferring the M-best diverse labelings for a binary (high-order) submodular energy of a graphical model. Recently, it was shown that this problem can be solved to a global optimum, for …
DiversityNonparametric Cointegrating Regression Functions with Endogeneity and Semi-Long Memory
This article develops nonparametric cointegrating regression models with endogeneity and semi-long memory. We assume that semi-long memory is produced in the regressor process by tempering of random shock coefficients. T…
regressionInference for multiple object tracking: A Bayesian nonparametric approach
In recent years, multi object tracking (MOT) problem has drawn attention to it and has been studied in various research areas. However, some of the challenging problems including time dependent cardinality, unordered mea…
Multi-Object TrackingMultiple Object TrackingObjectObject Tracking