Optimization of average precision with Maximal Figure-of-Merit Learning

We propose an efficient algorithm to directly optimize class average precision (AP) with a Maximal Figure-of-Merit (MFoM) learning scheme. AP is considered as a staircase function with respect to each individual sample score after rank ordering is applied to all samples. A combination of sigmoid fun...

Full description

Saved in:
Bibliographic Details
Main Authors: Ilseo Kim, Chin-Hui Lee
Format: Conference Proceeding
Language:English
Subjects:
Approximation algorithms
Approximation methods
automatic image annotation
average precision
Computational modeling
high-level image feature extraction
Manganese
Measurement
MFoM
Optimization
rank statistics
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose an efficient algorithm to directly optimize class average precision (AP) with a Maximal Figure-of-Merit (MFoM) learning scheme. AP is considered as a staircase function with respect to each individual sample score after rank ordering is applied to all samples. A combination of sigmoid functions is then used to approximate AP as a continuously differentiable function of the classified parameters used to compute the sample scores. Compared to pair-wise ranking comparisons, the computational complexity of the proposed MFoM-AP learning algorithm can be substantially reduced when estimating classifier parameters with a gradient descent algorithm. Experiments on the TRECVID 2005 high-level feature extraction task showed that the proposed algorithm can effectively improve the mean average precision (MAP) over 39 concepts from a baseline performance of 0.4039 with MFoM maximizing F1 to 0.4274 with MFoM-AP, while showing significant impromvements for 12 concepts as more than 10%.
ISSN:1551-2541
2378-928X
DOI:10.1109/MLSP.2011.6064638