Concept-dependent Image Annotation Via Existence-Based Multiple-Instance Learning

Conventional multiple-instance learning (MIL) algorithms for image annotation usually neglect concept dependence (i.e., the relationship between positive and negative concepts) and feature selection (i.e., which feature modality is suitable for a specific concept) problems, which have significant influence on the annotation performance. In this paper, we propose a novel concept-dependent algorithm for image annotation, named existence-based MIL (EBMIL), aiming at solving the above two problems in one scheme. In our EBMIL scheme, we give a new MIL formulation, named existence-based MIL, to explore the concept dependence in image annotation. Moreover, we give an optimization procedure in EBMIL, which is able to select different feature modalities for each concept under MIL settings. EBMIL achieves promising experimental results on the benchmark of COREL dataset with comparison to typical MIL algorithms.