paper-with-me

Papers

Visualizing Data using GTSNE

2021-08-03 · Songting Shi

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.

📄 PDF Abstract BibTeX arXiv:2108.01301

Code (1)

songtingstone/gtsne 공식 구현

Similar Papers 제목 키워드 기반

BTS: A Bi-Lingual Benchmark for Text Segmentation in the Wild

2022-01-01 · CVPR 2022 1 · Xixi Xu, Zhongang Qi, jianqi ma, Honglun Zhang 외

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 Transfer

Visualizing Bags of Vectors

2013-10-12 · Sriramkumar Balasubramanian, Raghuram Reddy Nagireddy

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

2019-04-04 · Jesse Vig

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 Modelling

An Incremental Dimensionality Reduction Method for Visualizing Streaming Multidimensional Data

2019-05-10 · Takanori Fujiwara, Jia-Kai Chou, Shilpika, Panpan Xu 외

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 Reduction

Visualizing and Comparing Convolutional Neural Networks

2014-12-20 · Wei Yu, Kuiyuan Yang, Yalong Bai, Hongxun Yao 외

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