CINIC-10 is not ImageNet or CIFAR-10

10/02/2018
by   Luke N. Darlow, et al.
0

In this brief technical report we introduce the CINIC-10 dataset as a plug-in extended alternative for CIFAR-10. It was compiled by combining CIFAR-10 with images selected and downsampled from the ImageNet database. We present the approach to compiling the dataset, illustrate the example images for different classes, give pixel distributions for each part of the repository, and give some standard benchmarks for well known models. Details for download, usage, and compilation can be found in the associated github repository.

READ FULL TEXT

page 4

page 5

page 6

page 7

page 8

page 9

research
07/27/2017

A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets

The original ImageNet dataset is a popular large-scale benchmark for tra...
research
06/29/2018

LTL Store: Repository of LTL formulae from literature and case studies

This continuously extended technical report collects and compares common...
research
05/06/2014

Some thoughts about benchmarks for NMR

The NMR community would like to build a repository of benchmarks to push...
research
05/24/2019

Magnetoresistive RAM for error resilient XNOR-Nets

We trained three Binarized Convolutional Neural Network architectures (L...
research
02/01/2017

ImageNet MPEG-7 Visual Descriptors - Technical Report

ImageNet is a large scale and publicly available image database. It curr...
research
05/27/2020

Github Data Exposure and Accessing Blocked Data using the GraphQL Security Design Flaw

This research study was conducted to illustrate how it is easily possibl...
research
02/12/2021

Semantically-Conditioned Negative Samples for Efficient Contrastive Learning

Negative sampling is a limiting factor w.r.t. the generalization of metr...

Please sign up or login with your details

Forgot password? Click here to reset