Finding Regions of Uncertainty in Learned Models: An Application to Face Detection
نویسنده
چکیده
After training statistical models to classify sets of data into predetermined classes, it is often di cult to interpret what the models have learned. This paper presents a novel approach for nding examples which lie on the decision boundaries of statistical models trained for classi cation. These examples provide insight into what the model has learned. Additionally, they can provide candidates for use as additional training data for improving the performance of the statistical models. By labeling the examples which lie on the decision boundaries, we provide information to the model in the regions in which it is most uncertain. The approaches presented in this paper are demonstrated on the real-world vision-based task of detecting faces in cluttered scenes.
منابع مشابه
A Novel Face Detection Method Based on Over-complete Incoherent Dictionary Learning
In this paper, face detection problem is considered using the concepts of compressive sensing technique. This technique includes dictionary learning procedure and sparse coding method to represent the structural content of input images. In the proposed method, dictionaries are learned in such a way that the trained models have the least degree of coherence to each other. The novelty of the prop...
متن کاملRelationship between Inflation and Inflation Uncertainty in Iran: An Application of SETAR-GARCH Model
The purpose of this paper is to investigate the relationship between the inflation and inflation uncertainty in Iran. Using mixed models of self-exciting threshold autoregressive (SETAR) and generalized autoregressive conditional heteroskedasticity (GARCH), the inflation behaviors are examined for the period 1990M05-2013M10. This approach allows testing the hypotheses of Friedman-Ball, Pourgera...
متن کاملDynamic Relationship between Inflation Uncertainty and Private Investment in Iran: An Application of VAR-GARCH-M Model
This paper empirically investigates the relationship between CPI inflation uncertainty, and private investment in the Iranian economy from 1988 to 2010 by using quarterly data. We employ a bivariate VAR(5)-GARCH(1,1)-in-mean with diagonal BEKK model to discover in a unified framework how are the interactions between the variables. In the model, conditional variance of inflation and private inve...
متن کاملSparse Structured Principal Component Analysis and Model Learning for Classification and Quality Detection of Rice Grains
In scientific and commercial fields associated with modern agriculture, the categorization of different rice types and determination of its quality is very important. Various image processing algorithms are applied in recent years to detect different agricultural products. The problem of rice classification and quality detection in this paper is presented based on model learning concepts includ...
متن کاملواسنجی و تحلیل عدمقطعیت یک مدل نیمهتوزیعی در یک منطقه نیمهخشک
Application of conceptual hydrological models is an important issue in watersheds for researchers, especially in arid and semi-arid regions. The hydrological behaviors are complicated in such watersheds and their calibration is more difficult. In this article, the conceptual and semi-distributed SWAT model is used for a semi-arid Nishabour watershed with 9350 km2 area. Streamflow simulation is ...
متن کامل