End-to-End Data Visualization by Metric Learning and Coordinate Transformation
This paper presents a deep nonlinear metric learning framework for data visualization on an image dataset. We propose the Triangular Similarity and prove its equivalence to the Cosine Similarity in measuring a data pair. Based on this novel similarity, a geometrically motivated loss function - the triangular loss - is then developed for optimizing a metric learning system comprising two identical CNNs. It is shown that this deep nonlinear system can be efficiently trained by a hybrid algorithm based on the conventional backpropagation algorithm. More interestingly, benefiting from classical manifold learning theories, the proposed system offers two different views to visualize the outputs, the second of which provides better classification results than the state-of-the-art methods in the visualizable spaces.
Code (0)
등록된 구현이 없습니다.
Tasks
Data VisualizationGeneral ClassificationMetric LearningSimilar Papers 제목 키워드 기반
Generalized Penalty for Circular Coordinate Representation
Topological Data Analysis (TDA) provides novel approaches that allow us to analyze the geometrical shapes and topological structures of a dataset. As one important application, TDA can be used for data visualization and …
Data VisualizationDimensionality ReductionTopological Data AnalysisPaCoNet: Deep Data Extraction for Parallel Coordinates
Extracting data from visualizations has long challenged computer vision, with current research focused on bar, line, and pie charts, among other low-dimensional visualizations. However, parallel coordinates as a widely u…
On the Residual-based Neural Network for Unmodeled Distortions in Coordinate Transformation
Coordinate transformation models often fail to account for nonlinear and spatially dependent distortions, leading to significant residual errors in geospatial applications. Here we propose a residual-based neural correct…
MentalBlackboard: Evaluating Spatial Visualization via Mathematical Transformations
Spatial visualization is the mental ability to imagine, transform, and manipulate the spatial characteristics of objects and actions. This intelligence is a part of human cognition where actions and perception are connec…
Consistent Representation Learning for High Dimensional Data Analysis
High dimensional data analysis for exploration and discovery includes three fundamental tasks: dimensionality reduction, clustering, and visualization. When the three associated tasks are done separately, as is often the…
ClusteringDimensionality ReductionRepresentation LearningVocal Bursts Intensity Prediction