Abstract | ||
---|---|---|
This paper introduces archetypal dictionaries for a self-taught learning framework for the application of landcover classification. Self-taught learning, an unsupervised representation learning method, is exploited to learn low-dimensional and discriminative higher-level features, which are used as input into a classification algorithm. Experiments are conducted using a multi-spectral Landsat 5 TM image of a study area in the north of Novo Progresso located in South America. Our results confirm that self-taught learning with archetypal dictionaries provide features, which can be used as input into a linear logistic regression classifier. The obtained classification accuracies are comparable to kernel-based classifier using the original features. |
Year | Venue | Keywords |
---|---|---|
2015 | 2015 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS) | self-taught learning, archetypal analysis, landcover classification |
Field | DocType | ISSN |
Kernel (linear algebra),Pattern recognition,Computer science,Support vector machine,Feature extraction,Artificial intelligence,Linear classifier,Classifier (linguistics),Discriminative model,Machine learning,Feature learning | Conference | 2153-6996 |
Citations | PageRank | References |
0 | 0.34 | 4 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ribana Roscher | 1 | 46 | 8.10 |
Christoph Römer | 2 | 13 | 2.71 |
Björn Waske | 3 | 435 | 24.75 |
Lutz Plümer | 4 | 141 | 23.12 |