In this paper, a multi-instance multi-label algorithm based on neural networks is proposed for image classification. The proposed algorithm, termed multi-instance multi-label neural network (MIMLNN), consists of two stages of MultiLayer Perceptrons (MLP). For multi-instance multi-label image classification, all the regional features are fed to the first-stage MLP, with one MLP copy processing one image region. After that, the MLP in the second stage incorporates the outputs of the first-stage MLPs to produce the final labels for the input image. The first-stage MLP is expected to model the relationship between regions and labels, while the second-stage MLP aims at capturing the label correlation for classification refinement. Error Back-Propagation (BP) approach is adopted to tune the parameters of MIMLNN. In view of that traditional gradient descent algorithm suffers from long-term dependency problem, a refined BP algorithm named Rprop is extended to effectively train MIMLNN. The experiments are conducted on a synthetic dataset and the Corel dataset. Experimental results demonstrate the superior performance of MIMLNN comparing with state-of-the-art algorithms for multi-instance multi-label image classification. Copyright © 2012 Elsevier B.V. All rights reserved.
CitationChen, Z., Chi, Z., Fu, H., & Feng, D. (2013). Multi-instance multi-label image classification: A neural approach. Neurocomputing, 99, 298-306. doi: 10.1016/j.neucom.2012.08.001
- Multi-instance multi-label learning
- Image classification
- Neural networks
- Synthetic data