Abstract
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.
Original language | English |
---|---|
Pages (from-to) | 298-306 |
Number of pages | 9 |
Journal | Neurocomputing |
Volume | 99 |
DOIs | |
Publication status | Published - 1 Jan 2013 |
Keywords
- Image classification
- Multi-instance multi-label learning
- Neural networks
- Synthetic data
ASJC Scopus subject areas
- Computer Science Applications
- Cognitive Neuroscience
- Artificial Intelligence