paper-with-me

홈 › Papers

Trace Quotient Meets Sparsity: A Method for Learning Low Dimensional Image Representations

2016-06-01 · CVPR 2016 6 · Xian Wei, Hao Shen, Martin Kleinsteuber

This paper presents an algorithm that allows to learn low dimensional representations of images in an unsupervised manner. The core idea is to combine two criteria that play important roles in unsupervised representation learning, namely sparsity and trace quotient. The former is known to be a convenient tool to identify underlying factors, and the latter is known as a disentanglement of underlying discriminative factors. In this work, we develop a generic cost function for learning jointly a sparsifying dictionary and a dimensionality reduction transformation. It leads to several counterparts of classic low dimensional representation methods, such as Principal Component Analysis, Local Linear Embedding, and Laplacian Eigenmap. Our proposed optimisation algorithm leverages the efficiency of geometric optimisation on Riemannian manifolds and a closed form solution to the elastic net problem.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Dimensionality ReductionDisentanglementRepresentation Learning

Similar Papers 제목 키워드 기반

Trace Quotient with Sparsity Priors for Learning Low Dimensional Image Representations

2018-10-08 · Xian Wei, Hao Shen, Martin Kleinsteuber

This work studies the problem of learning appropriate low dimensional image representations. We propose a generic algorithmic framework, which leverages two classic representation learning paradigms, i.e., sparse represe…

Data VisualizationDimensionality ReductionRepresentation Learning

A Trace Lasso Regularized L1-norm Graph Cut for Highly Correlated Noisy Hyperspectral Image

2018-07-22 · Ramanarayan Mohanty, S. L. Happy, Nilesh Suthar, Aurobinda Routray

This work proposes an adaptive trace lasso regularized L1-norm based graph cut method for dimensionality reduction of Hyperspectral images, called as `Trace Lasso-L1 Graph Cut' (TL-L1GC). The underlying idea of this meth…

Dimensionality Reduction

Isometric Quotient Variational Auto-Encoders for Structure-Preserving Representation Learning

2023-09-21 · NeurIPS 2023 11

We study structure-preserving low-dimensional representation of a data manifold embedded in a high-dimensional observation space based on variational auto-encoders (VAEs). We approach this by decomposing the data manifol…

Rapidly-Exploring Quotient-Space Trees: Motion Planning using Sequential Simplifications

2019-06-04 · Andreas Orthey, Marc Toussaint

Motion planning problems can be simplified by admissible projections of the configuration space to sequences of lower-dimensional quotient-spaces, called sequential simplifications. To exploit sequential simplifications,…

Motion Planning

A Benchmark for Sparse Coding: When Group Sparsity Meets Rank Minimization

2017-09-12 · Zhiyuan Zha, Xin Yuan, Bihan Wen, Jiantao Zhou 외

Sparse coding has achieved a great success in various image processing tasks. However, a benchmark to measure the sparsity of image patch/group is missing since sparse coding is essentially an NP-hard problem. This work …

Dictionary LearningImage InpaintingImage Restoration