Abstract
We study the problem of classifying images into a given, pre-determined taxonomy. This task can be elegantly translated into the structured learning framework. However, despite its power, structured learning has known limits in scalability due to its high memory requirements and slow training process. We propose an efficient approximation of the structured learning approach by an ensemble of local support vector machines (SVMs) that can be trained efficiently with standard techniques. A first theoretical discussion and experiments on toy-data allow to shed light onto why taxonomy-based classification can outperform taxonomy-free approaches and why an appropriately combined ensemble of local SVMs might be of high practical use. Further empirical results on subsets of Caltech256 and VOC2006 data indeed show that our local SVM formulation can effectively exploit the taxonomy structure and thus outperforms standard multi-class classification algorithms while it achieves on par results with taxonomy-based structured algorithms at a significantly decreased computing time.
| Original language | English |
|---|---|
| Pages (from-to) | 281-301 |
| Number of pages | 21 |
| Journal | International Journal of Computer Vision |
| Volume | 99 |
| Issue number | 3 |
| DOIs | |
| Publication status | Published - 2012 Sep 1 |
| Externally published | Yes |
Fingerprint
Keywords
- Multi-class object categorization
- Structure learning
- Support vector machine
- Taxonomies
ASJC Scopus subject areas
- Software
- Artificial Intelligence
- Computer Vision and Pattern Recognition
Cite this
On taxonomies for multi-class image categorization. / Binder, Alexander; Muller, Klaus; Kawanabe, Motoaki.
In: International Journal of Computer Vision, Vol. 99, No. 3, 01.09.2012, p. 281-301.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - On taxonomies for multi-class image categorization
AU - Binder, Alexander
AU - Muller, Klaus
AU - Kawanabe, Motoaki
PY - 2012/9/1
Y1 - 2012/9/1
N2 - We study the problem of classifying images into a given, pre-determined taxonomy. This task can be elegantly translated into the structured learning framework. However, despite its power, structured learning has known limits in scalability due to its high memory requirements and slow training process. We propose an efficient approximation of the structured learning approach by an ensemble of local support vector machines (SVMs) that can be trained efficiently with standard techniques. A first theoretical discussion and experiments on toy-data allow to shed light onto why taxonomy-based classification can outperform taxonomy-free approaches and why an appropriately combined ensemble of local SVMs might be of high practical use. Further empirical results on subsets of Caltech256 and VOC2006 data indeed show that our local SVM formulation can effectively exploit the taxonomy structure and thus outperforms standard multi-class classification algorithms while it achieves on par results with taxonomy-based structured algorithms at a significantly decreased computing time.
AB - We study the problem of classifying images into a given, pre-determined taxonomy. This task can be elegantly translated into the structured learning framework. However, despite its power, structured learning has known limits in scalability due to its high memory requirements and slow training process. We propose an efficient approximation of the structured learning approach by an ensemble of local support vector machines (SVMs) that can be trained efficiently with standard techniques. A first theoretical discussion and experiments on toy-data allow to shed light onto why taxonomy-based classification can outperform taxonomy-free approaches and why an appropriately combined ensemble of local SVMs might be of high practical use. Further empirical results on subsets of Caltech256 and VOC2006 data indeed show that our local SVM formulation can effectively exploit the taxonomy structure and thus outperforms standard multi-class classification algorithms while it achieves on par results with taxonomy-based structured algorithms at a significantly decreased computing time.
KW - Multi-class object categorization
KW - Structure learning
KW - Support vector machine
KW - Taxonomies
UR - http://www.scopus.com/inward/record.url?scp=84863619408&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84863619408&partnerID=8YFLogxK
U2 - 10.1007/s11263-010-0417-8
DO - 10.1007/s11263-010-0417-8
M3 - Article
VL - 99
SP - 281
EP - 301
JO - International Journal of Computer Vision
JF - International Journal of Computer Vision
SN - 0920-5691
IS - 3
ER -