DMCA
3-d object recognition with deep belief nets (2009)
Cached
Download Links
| Venue: | Advances in Neural Information Processing Systems 22 |
| Citations: | 63 - 8 self |
BibTeX
@INPROCEEDINGS{Nair093-dobject,
author = {Vinod Nair and Geoffrey E. Hinton},
title = {3-d object recognition with deep belief nets},
booktitle = {Advances in Neural Information Processing Systems 22},
year = {2009}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We introduce a new type of top-level model for Deep Belief Nets and evaluate it on a 3D object recognition task. The top-level model is a third-order Boltzmann machine, trained using a hybrid algorithm that combines both generative and discriminative gradients. Performance is evaluated on the NORB database (normalized-uniform version), which contains stereo-pair images of objects under different lighting conditions and viewpoints. Our model achieves 6.5 % error on the test set, which is close to the best published result for NORB (5.9%) using a convolutional neural net that has built-in knowledge of translation invariance. It substantially outperforms shallow models such as SVMs (11.6%). DBNs are especially suited for semi-supervised learning, and to demonstrate this we consider a modified version of the NORB recognition task in which additional unlabeled images are created by applying small translations to the images in the database. With the extra unlabeled data (and the same amount of labeled data as before), our model achieves 5.2 % error. 1
Keyphrases
deep belief net 3-d object recognition top-level model additional unlabeled image modified version shallow model discriminative gradient stereo-pair image small translation test set translation invariance different lighting condition hybrid algorithm object recognition task normalized-uniform version extra unlabeled data semi-supervised learning convolutional neural net built-in knowledge new type norb recognition task third-order boltzmann machine norb database
