Fast classification using sparse decision DAGs

06/27/2012 ∙ by Djalel Benbouzid, et al. ∙ 0 ∙ share

In this paper we propose an algorithm that builds sparse decision DAGs (directed acyclic graphs) from a list of base classifiers provided by an external learning method such as AdaBoost. The basic idea is to cast the DAG design task as a Markov decision process. Each instance can decide to use or to skip each base classifier, based on the current state of the classifier being built. The result is a sparse decision DAG where the base classifiers are selected in a data-dependent way. The method has a single hyperparameter with a clear semantics of controlling the accuracy/speed trade-off. The algorithm is competitive with state-of-the-art cascade detectors on three object-detection benchmarks, and it clearly outperforms them when there is a small number of base classifiers. Unlike cascades, it is also readily applicable for multi-class classification. Using the multi-class setup, we show on a benchmark web page ranking data set that we can significantly improve the decision speed without harming the performance of the ranker.

READ FULL TEXT

Enhancements of Multi-class Support Vector Machine Construction from Binary Learners using Generalization Performance

We propose several novel methods for enhancing the multi-class SVMs by a...
09/11/2013 ∙ by Patoomsiri Songsiri, et al. ∙ 0 ∙ share

read it
Enhancing Multi-Class Classification of Random Forest using Random Vector Functional Neural Network and Oblique Decision Surfaces

Both neural networks and decision trees are popular machine learning met...
02/05/2018 ∙ by Rakesh Katuwal, et al. ∙ 0 ∙ share

read it
DCSVM: Fast Multi-class Classification using Support Vector Machines

We present DCSVM, an efficient algorithm for multi-class classification ...
10/23/2018 ∙ by Duleep Rathgamage Don, et al. ∙ 0 ∙ share

read it
An ensemble of Density based Geometric One-Class Classifier and Genetic Algorithm

One of the most rising issues in recent machine learning research is One...
10/02/2020 ∙ by Do Gyun Kim, et al. ∙ 0 ∙ share

read it
Meta-Cal: Well-controlled Post-hoc Calibration by Ranking

In many applications, it is desirable that a classifier not only makes a...
05/10/2021 ∙ by Xingchen Ma, et al. ∙ 0 ∙ share

read it
Improving Human Activity Recognition Through Ranking and Re-ranking

We propose two well-motivated ranking-based methods to enhance the perfo...
12/11/2015 ∙ by Zhenzhong Lan, et al. ∙ 0 ∙ share

read it
DCMD: Distance-based Classification Using Mixture Distributions on Microbiome Data

Current advances in next generation sequencing techniques have allowed r...
03/29/2020 ∙ by Konstantin Shestopaloff, et al. ∙ 13 ∙ share

read it

Fast classification using sparse decision DAGs

Authors

Enhancements of Multi-class Support Vector Machine Construction from Binary Learners using Generalization Performance

Enhancing Multi-Class Classification of Random Forest using Random Vector Functional Neural Network and Oblique Decision Surfaces

DCSVM: Fast Multi-class Classification using Support Vector Machines

An ensemble of Density based Geometric One-Class Classifier and Genetic Algorithm

Meta-Cal: Well-controlled Post-hoc Calibration by Ranking

Improving Human Activity Recognition Through Ranking and Re-ranking

DCMD: Distance-based Classification Using Mixture Distributions on Microbiome Data

This week in AI