Adaptive Local Fusion with Neural Networks

Abstract

We propose a novel method for fusing different classifiers outputs. Our approach, called Context Extraction for Local Fusion with Neural Networks (CELF-NN), is a local approach that adapts Artificial Neural Network fusion method to different regions of the feature space. It is based on a novel objective function that combines context identification and multi-algorithm fusion criteria into a joint objective function. This objective function is defined and optimized to produce contexts as compact clusters via unsupervised clustering. Optimization of the objective function also provide an optimal local Neural Network for fusion within each context. Our initial experiments on semantic video indexing have indicated that the proposed fusion approach outperforms all individual classifiers and the global Neural Network fusion method.