Open AccessProceedings Article
Compute less to get more: using ORC to improve sparse filtering
Johannes Lederer,Sergio Guadarrama +1 more
- 25 Jan 2015
- pp 3797-3803
TL;DR: In this article, the Optimal Roundness Criterion (ORC) is proposed as a novel stopping criterion for sparse filtering, which 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 more
Abstract: 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 more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Developing Iris Recognition System for Smartphone Security
Lamiaa A. Elrefaei,Lamiaa A. Elrefaei,Doaa H. Hamid,Afnan A. Bayazed,Sara S. Bushnak,Shaikhah Y. Maasher +5 more
TL;DR: This paper develops and tests an iris recognition system for smartphones that uses eye images that rely on visible wavelength and seven different matching techniques are investigated to decide the most appropriate one the system will use to verify the user.
23
•Posted Content
On the Use of Sparse Filtering for Covariate Shift Adaptation
Fabio Massimo Zennaro,Ke Chen +1 more
TL;DR: It is shown that periodic sparse filtering can perform adaptation under the looser and more realistic requirement that the conditional distribution of the labels has a periodic structure, which may be satisfied, for instance, by user-dependent data sets.
2
A New Transfer Learning Method and its Application on Rotating Machine Fault Diagnosis Under Variant Working Conditions
TL;DR: A novel dataset distribution discrepancy measuring algorithm called high-order Kullback–Leibler (HKL) divergence is proposed and based on HKL divergence and transfer learning, a new fault diagnosis network which is robust to working condition variation is constructed.
References
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Regression Shrinkage and Selection via the Lasso
TL;DR: A new method for estimation in linear models called the lasso, which minimizes the residual sum of squares subject to the sum of the absolute value of the coefficients being less than a constant, is proposed.
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Ross Girshick,Jeff Donahue,Trevor Darrell,Jitendra Malik +3 more
- 23 Jun 2014
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.
•Dissertation
Learning Multiple Layers of Features from Tiny Images
Alex Krizhevsky
- 01 Jan 2009
TL;DR: In this paper, the authors describe how to train a multi-layer generative model of natural images, using a dataset of millions of tiny colour images, described in the next section.
Neocognitron: A Self Organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position
TL;DR: A neural network model for a mechanism of visual pattern recognition that is self-organized by “learning without a teacher”, and acquires an ability to recognize stimulus patterns based on the geometrical similarity of their shapes without affected by their positions.