A Nonparametric Bayesian Approach Toward Stacked Convolutional
Independent Component Analysis
release_ym7ddgrxprbdve56z6jyeycj34
by
Sotirios P. Chatzis
2014
Abstract
Unsupervised feature learning algorithms based on convolutional formulations
of independent components analysis (ICA) have been demonstrated to yield
state-of-the-art results in several action recognition benchmarks. However,
existing approaches do not allow for the number of latent components (features)
to be automatically inferred from the data in an unsupervised manner. This is a
significant disadvantage of the state-of-the-art, as it results in considerable
burden imposed on researchers and practitioners, who must resort to tedious
cross-validation procedures to obtain the optimal number of latent features. To
resolve these issues, in this paper we introduce a convolutional nonparametric
Bayesian sparse ICA architecture for overcomplete feature learning from
high-dimensional data. Our method utilizes an Indian buffet process prior to
facilitate inference of the appropriate number of latent features under a
hybrid variational inference algorithm, scalable to massive datasets. As we
show, our model can be naturally used to obtain deep unsupervised hierarchical
feature extractors, by greedily stacking successive model layers, similar to
existing approaches. In addition, inference for this model is completely
heuristics-free; thus, it obviates the need of tedious parameter tuning, which
is a major challenge most deep learning approaches are faced with. We evaluate
our method on several action recognition benchmarks, and exhibit its advantages
over the state-of-the-art.
In text/plain
format
Archived Files and Locations
application/pdf 515.6 kB
file_mws4klq4enae3epitq5mhrg7vy
|
arxiv.org (repository) web.archive.org (webarchive) |
1411.4423v1
access all versions, variants, and formats of this works (eg, pre-prints)