No more meta-parameter tuning in unsupervised sparse feature learning

24 Feb 2014  ·  Adriana Romero, Petia Radeva, Carlo Gatta ·

We propose a meta-parameter free, off-the-shelf, simple and fast unsupervised feature learning algorithm, which exploits a new way of optimizing for sparsity. Experiments on STL-10 show that the method presents state-of-the-art performance and provides discriminative features that generalize well.

PDF Abstract

Code
Add Remove Mark official

No code implementations yet. Submit your code now

Datasets

STL-10

Results from the Paper
Edit

Ranked #104 on Image Classification on STL-10

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Classification STL-10 No more meta-parameter tuning in unsupervised sparse feature learning Percentage correct 61 # 104
Compare

Methods
Add Remove

No methods listed for this paper. Add relevant methods here
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy