DMCA
On feature combination for multiclass object classification
Cached
Download Links
| Venue: | IN ICCV |
| Citations: | 259 - 5 self |
BibTeX
@INPROCEEDINGS{Gehler_onfeature,
author = {Peter Gehler and Sebastian Nowozin},
title = {On feature combination for multiclass object classification},
booktitle = {IN ICCV},
year = {},
publisher = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
A key ingredient in the design of visual object classification systems is the identification of relevant class specific aspects while being robust to intra-class variations. While this is a necessity in order to generalize beyond a given set of training images, it is also a very difficult problem due to the high variability of visual appearance within each class. In the last years substantial performance gains on challenging benchmark datasets have been reported in the literature. This progress can be attributed to two developments: the design of highly discriminative and robust image features and the combination of multiple complementary features based on different aspects such as shape, color or texture. In this paper we study several models that aim at learning the correct weighting of different features from training data. These include multiple kernel learning as well as simple baseline methods. Furthermore we derive ensemble methods inspired by Boosting which are easily extendable to several multiclass setting. All methods are thoroughly evaluated on object classification datasets using a multitude of feature descriptors. The key results are that even very simple baseline methods, that are orders of magnitude faster than learning techniques are highly competitive with multiple kernel learning. Furthermore the Boosting type methods are found to produce consistently better results in all experiments. We provide insight of when combination methods can be expected to work and how the benefit of complementary features can be exploited most efficiently.
Keyphrases
multiclass object classication feature combination multiple kernel simple baseline method visual object classification system high variability object classification datasets multiple complementary feature training image boosting type method relevant class specific aspect intra-class variation different aspect benchmark datasets visual appearance difficult problem several multiclass key result complementary feature robust image feature feature descriptor key ingredient combination method last year substantial performance gain correct weighting several model ensemble method different feature
