CVLGSep 16, 2014

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

arXiv:1409.4689v22 citations
Originality Incremental advance
AI Analysis

This work addresses efficiency and accuracy issues in image classification pipelines using Sparse Filtering, but it appears incremental as it builds on an existing method with a new stopping criterion.

The paper tackled the problem of improving Sparse Filtering for image classification by connecting its performance to spectral properties, leading to the introduction of the Optimal Roundness Criterion (ORC) as a novel stopping criterion. The result showed that ORC makes image classification with Sparse Filtering considerably faster and more accurate, though no concrete numbers were provided.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes