Candid Covariance-Free Incremental Principal Component Analysis

By J. Weng, Yilu Zhang, Wey-Shiuan Hwang. 2003

508 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

MgSvF: Multi-Grained Slow versus Fast Framework for Few-Shot Class-Incremental Learning (2020, methodology): “For concatenating features in the composite space, the transformation matrix can be constructed as Q ¼ P 1 0 0 P 2 (cid”
Background modeling and subtraction of dynamic scenes (2003, methodology): “We adapt the method developed by Weng et. al.”
Non-I.I.D. Multi-Instance Dimensionality Reduction by Learning a Maximum Bag Margin Subspace (2010, methodology): “…Component Analysis (PCA) (Devijver and Kittler 1982) which aims at finding the projection that maximize the data variance, along with some other similar algorithms (Weng, Zhang, and Hwang 2003) (Bartelmaos and Abed-Meraim 2008) (Xu et al. 2009) are a typical class of unsupervised DR methods.”
Incremental Slow Feature Analysis: Adaptive Low-Complexity Slow Feature Updating from High-Dimensional Input Streams (2012, background): “(For more information on comparisons, see Oja, 1992; Hyvärinen, Karhunen, & Oja, 2001; Weng et al., 2003).”
Incremental nonlinear dimensionality reduction by manifold learning (2006, methodology): “This differs from the previous work [50] where the matrix size is assumed to be constant.”
The Fast Convergence of Incremental PCA (2013, unknown): “We give finite-sampleconvergence rates for both.”
An intrinsic value system for developing multiple invariant representations with incremental slowness learning (2013, methodology): “Some details of these algorithms are described below, but more thorough descriptions can be found elsewhere [13], [20], [39], [68], [71].”
Incremental linear discriminant analysis for classification of data streams (2005, methodology): “[8] proposed a fast IPCA approximation algorithm computing the principle components of a sequence of samples incrementally without estimating the covariance matrix.”
Few-Shot Class-Incremental Learning via Feature Space Composition (2020, methodology): “Ours-pca”. Speciﬁcally, we compute the PCA transformation matrix P 1 with features of samples in base task (obtained by the base model). Another transformation matrix P 2 can be learned incrementally [57, 58] with samples from the subsequent tasks. Then we reduce the dimension to, e.g. half of the o”
Developmental Robotics: Theory and Experiments (2004, methodology): “, using the Candid Covariance-free Incremental Principal Component Analysis (CCIPCA).(60) More detail about sensory mapping is explained in Ref.”