Name
Title | ||
|---|---|---|
Efficient learning of sparse, distributed, convolutional feature representations for object recognition |
Abstract | ||
|---|---|---|
Informative image representations are important in achieving state-of-the-art performance in object recognition tasks. Among feature learning algorithms that are used to develop image representations, restricted Boltzmann machines (RBMs) have good expressive power and build effective representations. However, the difficulty of training RBMs has been a barrier to their wide use. To address this difficulty, we show the connections between mixture models and RBMs and present an efficient training method for RBMs that utilize these connections. To the best of our knowledge, this is the first work showing that RBMs can be trained with almost no hyperparameter tuning to provide classification performance similar to or significantly better than mixture models (e.g., Gaussian mixture models). Along with this efficient training, we evaluate the importance of convolutional training that can capture a larger spatial context with less redundancy, as compared to non-convolutional training. Overall, our method achieves state-of-the-art performance on both Caltech 101 / 256 datasets using a single type of feature. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/ICCV.2011.6126554 | ICCV |
Keywords | Field | DocType |
gaussian mixture model,boltzmann machines,image representation,efficient training,convolutional feature representation,feature representations,learning (artificial intelligence),efficient training method,training rbms,convolutional training,mixture models,restricted boltzmann machines,caltech 101-256 datasets,image classification,informative image representation,informative image representations,object recognition,classification performance,efficient learning,mixture model,state-of-the-art performance,learning,hyperparameter tuning,clustering algorithms,convolutional codes,boltzmann machine,learning artificial intelligence,spatial context,encoding,convolutional code,expressive power,feature extraction | Boltzmann machine,Caltech 101,Computer science,Artificial intelligence,Contextual image classification,Computer vision,Hyperparameter,Pattern recognition,Feature extraction,Mixture model,Feature learning,Machine learning,Cognitive neuroscience of visual object recognition | Conference |
Volume | Issue | ISSN |
2011 | 1 | 1550-5499 |
ISBN | Citations | PageRank |
978-1-4577-1101-5 | 63 | 3.62 |
References | Authors | |
16 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kihyuk Sohn | 1 | 629 | 32.95 |
| Dae Yon Jung | 2 | 63 | 3.62 |
| Honglak Lee | 3 | 6247 | 398.39 |
| Alfred O. Hero III | 4 | 2600 | 301.12 |