A kernelized maximal-figure-of-merit learning approach based on subspace distance minimization

Byun, Byungki; Lee, Chin‐Hui

doi:10.1109/icassp.2011.5946732

Cited by 1 publication

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are mainly two branches of methods to deal with the problem. One is to use nonlinear discriminant function like quadratic functions [11], and the other is to apply kernel functions to map features to high dimension Hilbert space [12]. Using a nonlinear discriminant function will make the objective function hard to solve, while kernelization approaches need to deal with the increased dimensions when there are hundreds of thousands of training samples.…”

Section: Introductionmentioning

confidence: 99%

A maximal figure-of-merit learning approach to maximizing mean average precision with deep neural network based classifiers

Huang

Cheng

et al. 2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

We propose a maximal figure-of-merit (MFoM) learning framework to directly maximize mean average precision (MAP) which is a key performance metric in many multi-class classification tasks. Conventional classifiers based on support vector machines cannot be easily adopted to optimize the MAP metric. On the other hand, classifiers based on deep neural networks (DNNs) have recently been shown to deliver a great discrimination capability in automatic speech recognition and image classification as well. However, DNNs are usually optimized with the minimum cross entropy criterion. In contrast to most conventional classification methods, our proposed approach can be formulated to embed DNNs and MAP into the objective function to be optimized during training. The combination of the proposed maximum MAP (MMAP) technique and DNNs introduces nonlinearity to the linear discriminant function (LDF) in order to increase the flexibility and discriminant power of the original MFoM-trained LDF based classifiers. Tested on both automatic image annotation and audio event classification, the experimental results show consistent improvements of MAP on both datasets when compared with other state-of-the-art classifiers without using MMAP.

show abstract

Section: Introductionmentioning

confidence: 99%