Estimating a Kernel Fisher Discriminant in the Presence of Label Noise
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Hierarchical clustering of WWW image search results using visual, textual and link information
Proceedings of the 12th annual ACM international conference on Multimedia
Class Noise vs. Attribute Noise: A Quantitative Study
Artificial Intelligence Review
Formulating Semantic Image Annotation as a Supervised Learning Problem
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Semantic knowledge extraction and annotation for web images
Proceedings of the 13th annual ACM international conference on Multimedia
Generalized Discriminant Analysis Using a Kernel Approach
Neural Computation
Local Fisher discriminant analysis for supervised dimensionality reduction
ICML '06 Proceedings of the 23rd international conference on Machine learning
AnnoSearch: Image Auto-Annotation by Search
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
Real-time computerized annotation of pictures
MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
Multiple Bernoulli relevance models for image and video annotation
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
| Hi-index | 0.00 |
Training data acquisition is a problem in large scale statistical learning based web image annotation. A common idea is to build a large training set by analyzing the web content automatically. However, the noisy data is unavoidable involved in this kind of approach. In this paper, we present a novel web image annotation method based on noisy training set using Mixture Component based Local Fisher Discriminant Analysis (MLFDA). In our method, image annotation is viewed as a multiple class classification problem. To alleviate the influence of the noisy data, the separating hyper planes between different classes are learned by kernel-based local fisher discriminant analysis. Then the mixture components for each class are estimated in the subspace, where the noisy modals will gain small weights and play less important role in classification. The experimental results on a real-world web data set of 4000 images show that our method outperforms MBRM [3] and SVM-based method with F1 measure improving 83% and 18% respectively.