Two-stage optimal component analysis

Wu, Yiming; Liu, Xiuwen; Mio, Washington; Gallivan, Kyle A.

doi:10.1016/j.cviu.2007.04.005

Cited by 4 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MULTI-STAGE OCA In our previous work, similar with the two-stage LDA methods presented in [10], a two-stage OCA method is proposed to deal with the heavy computational cost problem [11]. In the first stage of this method, the dimension of the input data is reduced using certain well-known dimensional reduction methods, such as PCA, ICA, LDA, RCA, QR, etc.…”

Section: Optimal Component Analysismentioning

confidence: 99%

See 1 more Smart Citation

Multi-Stage Optimal Component Analysis

Liu

Mio

2007

2007 International Joint Conference on Neural Networks

Self Cite

View full text Add to dashboard Cite

Optimal component analysis (OCA) uses a stochastic gradient optimization process to find optimal representations for general criteria and shows good performance in object recognition applications. However, OCA often requires extensive computation for gradient estimation and linear representation updating. To significantly reduce the required computation, in this paper, a multi-stage learning process is proposed which decomposes the original optimization problem into several levels. As the learning process at each level starts with a good initial point obtained from next level, the multistage OCA algorithm can speed up the original algorithm significantly and make OCA learning feasible for many applications. We illustrate the effectiveness of the proposed method on the application of face classification.

show abstract

Section: Optimal Component Analysismentioning

confidence: 99%

“…In our previous work, a two-stage strategy is proposed to deal with this problem [11]. In this method, the input data is first reduced to a lower dimension using dimension reduction methods like PCA, LDA, etc., then OCA search is performed in the reduced space.…”

Section: Introductionmentioning

confidence: 99%