Abstract | ||
---|---|---|
Image recognition with incomplete data is a well-known hard problem in multimedia content analysis. This paper proposes a novel deep learning technique called semiconducting bilinear deep belief networks (SBDBN) by referencing human's visual cortex and intelligent perception. Inheriting from deep models, SBDBN simulates the laminar structure of human's cerebral cortex and the neural loop in human's visual areas. To address the special difficulties of image recognition with incomplete data, we design a novel second-order deep architecture with semiconducting restricted boltzmann machines. Moreover, two peaks activation of human's perception is implemented by three learning stages of semiconducting bilinear discriminant initialization, greedy layer-wise reconstruction, and global fine-tuning. Owing to exploiting the embedding information according to the reliable features rather than any completion of missing features, the proposed SBDBN has demonstrated outstanding recognition ability on two standard datasets and one constructed dataset, comparing with both incomplete image recognition techniques and existing deep learning models. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1145/2324796.2324836 | ICMR |
Keywords | Field | DocType |
bilinear deep learning,learning stage,incomplete image recognition technique,novel second-order deep architecture,referencing human,incomplete data,image recognition,deep model,proposed sbdbn,outstanding recognition ability,bilinear deep belief network,belief network,second order,boltzmann machine,deep learning | Boltzmann machine,Computer science,Deep belief network,Artificial intelligence,Deep learning,Computer vision,Embedding,Pattern recognition,Visual cortex,Initialization,Perception,Machine learning,Bilinear interpolation | Conference |
Citations | PageRank | References |
3 | 0.39 | 15 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sheng-hua Zhong | 1 | 220 | 18.58 |
Yan Liu | 2 | 181 | 19.10 |
Fu-lai Chung | 3 | 244 | 34.50 |
Gangshan Wu | 4 | 275 | 36.63 |