Hierarchical Growing Cell Structures: TreeGCS
IEEE Transactions on Knowledge and Data Engineering
A Self-Organizing Network that Can Follow Non-stationary Distributions
ICANN '97 Proceedings of the 7th International Conference on Artificial Neural Networks
A self-organising network that grows when required
Neural Networks - New developments in self-organizing maps
Video Google: A Text Retrieval Approach to Object Matching in Videos
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Scalable Recognition with a Vocabulary Tree
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
80 Million Tiny Images: A Large Data Set for Nonparametric Object and Scene Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Towards Scalable Dataset Construction: An Active Learning Approach
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Mixed-initiative in human augmented mapping
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
SURF: speeded up robust features
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
View-tuned approximate partial matching kernel from hierarchical growing neural gases
ICANN'11 Proceedings of the 21st international conference on Artificial neural networks - Volume Part II
Hi-index | 0.00 |
The Growing Neural Gas (GNG) algorithm is able to perform continuous vector quantization for an unknown distribution while preserving the topological structure of the input space. This makes the GNG attractive for online learning of visual codebooks. However, mapping an input vector to a reference vector is quite expensive and requires an iteration through the entire codebook. We propose a hierarchical extension of the Growing Neural Gas algorithm for online one-shot learning of visual vocabularies. The method intrinsically supports mapping input vectors to codewords in sub-linear time. Further, our extension avoids overfitting and locally keeps track of the topology of the input space. The algorithm is evaluated on both, low dimensional simulated data and high dimensional real world data.