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

• 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
• ISSN: 1551-2541; 2378-928X
• DOI: 10.1109/MLSP.2011.6064638

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%.