Bag-of-Features Codebook Generation by Self-Organisation
WSOM '09 Proceedings of the 7th International Workshop on Advances in Self-Organizing Maps
New clustering algorithms for the support vector machine based hierarchical classification
Pattern Recognition Letters
A coarse-to-fine taxonomy of constellations for fast multi-class object detection
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Hierarchical annotation of medical images
Pattern Recognition
Semantic hierarchies for image annotation: A survey
Pattern Recognition
Efficient classification of images with taxonomies
ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part III
On Taxonomies for Multi-class Image Categorization
International Journal of Computer Vision
Sparselet models for efficient multiclass object detection
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
The pooled NBNN kernel: beyond image-to-class and image-to-image
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Efficient discriminative learning of class hierarchy for many class prediction
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Exclusive visual descriptor quantization
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Image categorization using a semantic hierarchy model with sparse set of salient regions
Frontiers of Computer Science: Selected Publications from Chinese Universities
A semantic image classifier based on hierarchical fuzzy association rule mining
Multimedia Tools and Applications
| Hi-index | 0.00 |
Class hierarchies are commonly used to reduce the complexity of the classification problem. This is crucial when dealing with a large number of categories. In this work, we evaluate class hierarchies currently constructed for visual recognition. We show that top-down as well as bottom-up approaches, which are commonly used to automatically construct hierarchies, incorporate assumptions about the separability of classes. Those assumptions do not hold for visual recognition of a large number of object categories. We therefore propose a modification which is appropriate for most top-down approaches. It allows to construct class hierarchies that postpone decisions in the presence of uncertainty and thus provide higher recognition accuracy. We also compare our method to a one-against-all approach and show how to control the speed-for-accuracy trade-off with our method. For the experimental evaluation, we use the Caltech-256 visual object classes dataset and compare to state-of-the-art methods.