A Nonparametric Bayesian Approach Toward Stacked Convolutional Independent Component Analysis

by   Sotirios P. Chatzis, et al.

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.


page 1

page 2

page 3

page 4


Unsupervised Representation Learning by Predicting Image Rotations

Over the last years, deep convolutional neural networks (ConvNets) have ...

Pedestrian Detection with Unsupervised Multi-Stage Feature Learning

Pedestrian detection is a problem of considerable practical interest. Ad...

Anticipating human actions by correlating past with the future with Jaccard similarity measures

We propose a framework for early action recognition and anticipation by ...

Deep Learning on Lie Groups for Skeleton-based Action Recognition

In recent years, skeleton-based action recognition has become a popular ...

The convergent Indian buffet process

We propose a new Bayesian nonparametric prior for latent feature models,...

Adaptive Nonparametric Variational Autoencoder

Clustering is used to find structure in unlabeled data by grouping simil...

Deep Network Regularization via Bayesian Inference of Synaptic Connectivity

Deep neural networks (DNNs) often require good regularizers to generaliz...

Please sign up or login with your details

Forgot password? Click here to reset