Neural method for Explicit Mapping of Quasi-curvature Locally Linear Embedding in image retrieval

2017/03/11 by Shenglan Liu, Liu, Shenglan, Jun Wu +5
Computer Science · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face and Expression Recognition #Image Retrieval and Classification Techniques

paper · pdf · doi:10.48550/arxiv.1703.03957

openalex publication_date 2017/03/11 · openalex created_date 2017/04/14 · openalex updated_date 2026/07/28

Abstract

This paper proposed a new explicit nonlinear dimensionality reduction using neural networks for image retrieval tasks. We first proposed a Quasi-curvature Locally Linear Embedding (QLLE) for training set. QLLE guarantees the linear criterion in neighborhood of each sample. Then, a neural method (NM) is proposed for out-of-sample problem. Combining QLLE and NM, we provide a explicit nonlinear dimensionality reduction approach for efficient image retrieval. The experimental results in three benchmark datasets illustrate that our method can get better performance than other state-of-the-art out-of-sample methods.

Citations

• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Survey of Clustering Algorithms
• Perceptual uniform descriptor and Ranking on manifold: A bridge between image representation and ranking for image retrieval

Related

• Scalable Nonlinear Embeddings for Semantic Category-based Image Retrieval
• RAE: A Neural Network Dimensionality Reduction Method for Nearest Neighbors Preservation in Vector Search
• Nonlinear Supervised Dimensionality Reduction via Smooth Regular\n Embeddings
• LoFi: Neural Local Fields for Scalable Image Reconstruction
• An Iterative Locally Linear Embedding Algorithm