F
Frédéric Ratle
Researcher at University of Lausanne
Publications - 14
Citations - 2326
Frédéric Ratle is an academic researcher from University of Lausanne. The author has contributed to research in topics: Support vector machine & Contextual image classification. The author has an hindex of 10, co-authored 14 publications receiving 2120 citations.
Papers
More filters
Book ChapterDOI
Deep Learning via Semi-Supervised Embedding
TL;DR: Nonlinear embedding algorithms popular for use with "shallow" semi-supervised learning techniques such as kernel methods can be easily applied to deep multi-layer architectures, either as a regularizer at the output layer, or on each layer of the architecture.
Proceedings ArticleDOI
Deep learning via semi-supervised embedding
TL;DR: It is shown how nonlinear embedding algorithms popular for use with shallow semi-supervised learning techniques such as kernel methods can be applied to deep multilayer architectures, either as a regularizer at the output layer, or on each layer of the architecture.
Journal ArticleDOI
Active Learning Methods for Remote Sensing Image Classification
TL;DR: Two active learning algorithms for semiautomatic definition of training samples in remote sensing image classification, based on predefined heuristics, are proposed, which reach the same level of accuracy as larger data sets.
Journal ArticleDOI
Semisupervised Neural Networks for Efficient Hyperspectral Image Classification
TL;DR: The proposed approach gives rise to an operational classifier, as opposed to previously presented transductive or Laplacian support vector machines (TSVM or LapSVM, respectively), which constitutes a general framework for building computationally efficient semisupervised methods.
Journal ArticleDOI
Multisource Composite Kernels for Urban-Image Classification
TL;DR: Weighted summations of kernels accounting for separate sources of spectral and spatial information are analyzed and compared to classical approaches such as pure spectral classification or stacked approaches using all the features in a single vector.