Compute Less to Get More: Using ORC to Improve Sparse Filtering

09/16/2014
by   Johannes Lederer, et al.
0

Sparse Filtering is a popular feature learning algorithm for image classification pipelines. In this paper, we connect the performance of Sparse Filtering with spectral properties of the corresponding feature matrices. This connection provides new insights into Sparse Filtering; in particular, it suggests early stopping of Sparse Filtering. We therefore introduce the Optimal Roundness Criterion (ORC), a novel stopping criterion for Sparse Filtering. We show that this stopping criterion is related with pre-processing procedures such as Statistical Whitening and demonstrate that it can make image classification with Sparse Filtering considerably faster and more accurate.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/08/2013

A new stopping criterion for the mean shift iterative algorithm

The mean shift iterative algorithm was proposed in 2006, for using the e...
research
10/27/2021

A sequential estimation problem with control and discretionary stopping

We show that "full-bang" control is optimal in a problem that combines f...
research
06/11/2013

Stopping Criterion for the Mean Shift Iterative Algorithm

Image segmentation is a critical step in computer vision tasks constitut...
research
09/13/2019

DARTS+: Improved Differentiable Architecture Search with Early Stopping

Recently, there has been a growing interest in automating the process of...
research
12/16/2015

Effects of GIMP Retinex Filtering Evaluated by the Image Entropy

A GIMP Retinex filtering can be used for enhancing images, with good res...
research
04/13/2018

Value Iteration for Simple Stochastic Games: Stopping Criterion and Learning Algorithm

Simple stochastic games can be solved by value iteration (VI), which yie...
research
06/26/2020

Q-Learning with Differential Entropy of Q-Tables

It is well-known that information loss can occur in the classic and simp...

Please sign up or login with your details

Forgot password? Click here to reset