Visualizing Data using GTSNE
We present a new method GTSNE to visualize high-dimensional data points in the two dimensional map. The technique is a variation of t-SNE that produces better visualizations by capturing both the local neighborhood structure and the macro structure in the data. This is particularly important for high-dimensional data that lie on continuous low-dimensional manifolds. We illustrate the performance of GTSNE on a wide variety of datasets and compare it the state of art methods, including t-SNE and UMAP. The visualizations produced by GTSNE are better than those produced by the other techniques on almost all of the datasets on the macro structure preservation.
Code (1)
Similar Papers 제목 키워드 기반
BTS: A Bi-Lingual Benchmark for Text Segmentation in the Wild
As a prerequisite of many text-related tasks such as text erasing and text style transfer, text segmentation arouses more and more attention recently. Current researches mainly focus on only English characters and di…
SegmentationStyle TransferText SegmentationText Style TransferVisualizing Bags of Vectors
The motivation of this work is two-fold - a) to compare between two different modes of visualizing data that exists in a bag of vectors format b) to propose a theoretical model that supports a new mode of visualizing dat…
Visualizing Attention in Transformer-Based Language Representation Models
We present an open-source tool for visualizing multi-head self-attention in Transformer-based language representation models. The tool extends earlier work by visualizing attention at three levels of granularity: the att…
Language ModellingAn Incremental Dimensionality Reduction Method for Visualizing Streaming Multidimensional Data
Dimensionality reduction (DR) methods are commonly used for analyzing and visualizing multidimensional data. However, when data is a live streaming feed, conventional DR methods cannot be directly used because of their c…
Dimensionality ReductionVisualizing and Comparing Convolutional Neural Networks
Convolutional Neural Networks (CNNs) have achieved comparable error rates to well-trained human on ILSVRC2014 image classification task. To achieve better performance, the complexity of CNNs is continually increasing wit…
ClassificationGeneral Classificationimage-classificationImage Classification