CIFAR-100

Dataset Information
Modalities
Images
Languages
Chinese
Introduced
2009
License
Unknown
Homepage
Official Website
Contents

Overview

The CIFAR-100 dataset (Canadian Institute for Advanced Research, 100 classes) is a subset of the Tiny Images dataset and consists of 60000 32x32 color images. The 100 classes in the CIFAR-100 are grouped into 20 superclasses. There are 600 images per class. Each image comes with a "fine" label (the class to which it belongs) and a "coarse" label (the superclass to which it belongs). There are 500 training images and 100 testing images per class.

The criteria for deciding whether an image belongs to a class were as follows:

  • The class name should be high on the list of likely answers to the question “What is in this picture?”
  • The image should be photo-realistic. Labelers were instructed to reject line drawings.
  • The image should contain only one prominent instance of the object to which the class refers.
  • The object may be partially occluded or seen from an unusual viewpoint as long as its identity is still clear to the labeler.

Source: https://www.cs.toronto.edu/~kriz/cifar.html
Image Source: https://www.cs.toronto.edu/~kriz/cifar.html

Variants: cifar100, Unlabeled CIFAR-10 vs CIFAR-100, CIFAR-100 ResNet-18 - 200 Epochs, CIFAR-10, 2000 Labeled Samples, cifar-100, 10000 Labels, One-class CIFAR-100, Cifar100 (20 tasks), CIFAR100 5-way (1-shot), CIFAR-100-LT (ρ=100), CIFAR-100-LT (ρ=10), CIFAR-100, 5000Labels, CIFAR-100, 400 Labels, CIFAR-100, 2500 Labels, CIFAR-100, 1000 Labels, CIFAR-100 - 50 classes + 50 steps of 1 class, CIFAR-100 - 50 classes + 5 steps of 10 classes, CIFAR-100 - 50 classes + 25 steps of 2 classes, CIFAR-100 - 50 classes + 10 steps of 5 classes, CIFAR-100

Associated Benchmarks

This dataset is used in 15 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
Image Classification MANO-tiny Linear Attention with Global Context: … 2025-07-03
Image Clustering PRO-DSC Exploring a Principled Framework for … 2025-03-21
Image Classification ResNet50 (FSGDM) On the Performance Analysis of … 2024-11-29
Image Classification ABNet-2G-R0 ANDHRA Bandersnatch: Training Neural Networks … 2024-11-28
Image Classification ABNet-2G-R3 ANDHRA Bandersnatch: Training Neural Networks … 2024-11-28
Image Classification ABNet-2G-R3-Combined ANDHRA Bandersnatch: Training Neural Networks … 2024-11-28
Image Classification ABNet-2G-R1 ANDHRA Bandersnatch: Training Neural Networks … 2024-11-28
Image Classification ABNet-2G-R2 ANDHRA Bandersnatch: Training Neural Networks … 2024-11-28
Image Classification ResCNet-50 Deep Feature Response Discriminative Calibration 2024-11-16
Image Classification DGMMC-S Performance of Gaussian Mixture Model … 2024-10-17
Image Clustering ITAE Improving Image Clustering with Artifacts … 2024-10-07
Image Classification ResNet-110 (SAP) Stochastic Subsampling With Average Pooling 2024-09-25
Adversarial Attack multi-resolution self-ensembles Ensemble everything everywhere: Multi-scale aggregation … 2024-08-08
Adversarial Attack 3-ensemble of multi-resolution self-ensembles Ensemble everything everywhere: Multi-scale aggregation … 2024-08-08
Image Clustering DPAC Deep Online Probability Aggregation Clustering 2024-07-07
Image Clustering SPICE-BPA The Balanced-Pairwise-Affinities Feature Transform 2024-06-25
Image Clustering TURTLE (CLIP + DINOv2) Let Go of Your Labels … 2024-06-11
Zero-Shot Learning ZLaP* Label Propagation for Zero-shot Classification … 2024-04-05
Zero-Shot Learning ZLaP Label Propagation for Zero-shot Classification … 2024-04-05
Knowledge Distillation shufflenet-v2(T:resnet-32x4, S:shufflenet-v2) Logit Standardization in Knowledge Distillation 2024-03-03

Research Papers

Recent papers with results on this dataset:

External Links: