The UMAP algorithm is competitive with t-SNE for visualization quality, and arguably preserves more of the global structure with superior run time performance.

11442

Content

rwightman/pytorch-image-models

2 papers 29,671

benedekrozemberczki/karateclub

2 papers 2,084

clementchadebec/benchmark_VAE

2 papers 1,675

Automunge/AutoMunge

2 papers 163

faceonlive/ai-research

2 papers 124

mathLab/ATHENA

2 papers 50

GoodSounds

0

Adversarial Autoencoders

I. Goodfellow, Jonathon Shlens, N. Jaitly, Alireza Makhzani•Tue Nov 17 2015

It is shown how the adversarial autoencoder can be used in applications such as semi-supervised classification, disentangling style and content of images, unsupervised clustering, dimensionality reduction and data visualization.

2343 0

Paper Graph

XGBoost: A Scalable Tree Boosting System

Tianqi Chen, Carlos Guestrin•Tue Mar 08 2016

This paper proposes a novel sparsity-aware algorithm for sparse data and weighted quantile sketch for approximate tree learning and provides insights on cache access patterns, data compression and sharding to build a scalable tree boosting system called XGBoost.

48813 0

Paper Graph

Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering

Bo Yang, Xiao Fu, N. Sidiropoulos, Mingyi Hong•Fri Oct 14 2016

A joint DR and K-means clustering approach in which DR is accomplished via learning a deep neural network (DNN) while exploiting theDeep neural network's ability to approximate any nonlinear function is proposed.

943 0

Paper Graph

ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

W. Zuo, Peng Fei Zhu, Q. Hu, Qilong Wang, Banggu Wu, P. Li•Mon Oct 07 2019

This paper proposes an Efficient Channel Attention (ECA) module, which only involves a handful of parameters while bringing clear performance gain, and develops a method to adaptively select kernel size of 1D convolution, determining coverage of local cross-channel interaction.

5364 0

Paper Graph

CatBoost: unbiased boosting with categorical features

Gleb Gusev, L. Ostroumova, A. Vorobev, Anna Veronika Dorogush, Andrey Gulin•Tue Jun 27 2017

This paper presents the key algorithmic techniques behind CatBoost, a new gradient boosting toolkit and provides a detailed analysis of this problem and demonstrates that proposed algorithms solve it effectively, leading to excellent empirical results.

4869 0

Paper Graph

Rethinking Spatial Dimensions of Vision Transformers

Sangdoo Yun, Byeongho Heo, Dongyoon Han, Sanghyuk Chun, Junsuk Choe, Seong Joon Oh•Mon Mar 29 2021

A novel Pooling-based Vision Transformer (PiT) is proposed, which achieves the improved model capability and generalization performance against ViT and outperforms the baseline on several tasks such as image classification, object detection and robustness evaluation.

679 0

Paper Graph

Efficient Algorithms for t-distributed Stochastic Neighborhood Embedding

G. Linderman, M. Rachh, J. Hoskins, S. Steinerberger, Y. Kluger•Sat Dec 31 2016

Out-of-core randomized principal component analysis (oocPCA) is presented, so that the top principal components of a dataset can be computed without ever fully loading the matrix, hence allowing for t-SNE of large datasets to be computed on resource-limited machines.

103 0

Paper Graph

ZOO: Zeroth Order Optimization Based Black-box Attacks to Deep Neural Networks without Training Substitute Models

Cho-Jui Hsieh, Pin-Yu Chen, Yash Sharma, Jinfeng Yi, Huan Zhang•Sun Aug 13 2017

An effective black-box attack that also only has access to the input (images) and the output (confidence scores) of a targeted DNN is proposed, sparing the need for training substitute models and avoiding the loss in attack transferability.

2101 0

Paper Graph

Adding a benchmark result helps the community track progress.