Transductive Multi-Instance Multi-Label learning algorithm with application to automatic image annotation

• Published in: Expert systems with applications Vol. 37; no. 1; pp. 661 - 670
• Main Authors: Feng, Songhe, Xu, De
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 2010
• Subjects: Automatic image annotation; Gaussian mixture model; Manifold-ranking; Multi-Instance Multi-Label learning; Reinforced diverse density algorithm; Transductive learning; Transductive learning; Multi-Instance Multi-Label learning; Automatic image annotation; Manifold-ranking; Gaussian mixture model; Reinforced diverse density algorithm
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2009.06.111

Automatic image annotation has emerged as an important research topic due to its potential application on both image understanding and web image search. Due to the inherent ambiguity of image-label mapping and the scarcity of training examples, the annotation task has become a challenge to systematically develop robust annotation models with better performance. From the perspective of machine learning, the annotation task fits both multi-instance and multi-label learning framework due to the fact that an image is usually described by multiple semantic labels (keywords) and these labels are often highly related to respective regions rather than the entire image. In this paper, we propose an improved Transductive Multi-Instance Multi-Label (TMIML) learning framework, which aims at taking full advantage of both labeled and unlabeled data to address the annotation problem. The experiments over the well known Corel 5000 data set demonstrate that the proposed method is beneficial in the image annotation task and outperforms most existing image annotation algorithms.