STL-10

Name: STL-10
Published: 2011-01-01
License: Custom (attribution + ImageNet license)

Self-Taught Learning 10

Dataset Information

Modalities

Images

Introduced

2011

License

Custom (attribution + ImageNet license)

Homepage

Official Website

Contents

Overview
Associated Benchmarks
Recent Benchmark Submissions
Research Papers

Overview

The STL-10 is an image dataset derived from ImageNet and popularly used to evaluate algorithms of unsupervised feature learning or self-taught learning. Besides 100,000 unlabeled images, it contains 13,000 labeled images from 10 object classes (such as birds, cats, trucks), among which 5,000 images are partitioned for training while the remaining 8,000 images for testing. All the images are color images with 96×96 pixels in size.

Source: Unsupervised Feature Learning with C-SVDDNet
Image Source: https://cs.stanford.edu/~acoates/stl10/

Variants: STL-10

Associated Benchmarks

This dataset is used in 17 benchmarks:

Image Generation - Metrics: FID, Inception score, Model Size (MB), Recall, NFE
Anomaly Detection - Metrics: ROC AUC
Neural Architecture Search - Metrics: Accuracy (%), FLOPS, PARAMS
Image Clustering - Metrics: Accuracy, NMI, ARI, Train Split, Backbone
Image Compression - Metrics: Bit rate
Image Classification - Metrics: Percentage correct, FLOPS, PARAMS
Out-of-Distribution Detection - Metrics: Percentage correct
Fine-Grained Image Classification - Metrics: Accuracy
Self-Supervised Learning - Metrics: Accuracy
Contrastive Learning - Metrics: Accuracy (Top-1)
Unsupervised Anomaly Detection - Metrics: AUC-ROC
Semi-Supervised Image Classification - Metrics: Accuracy
Unsupervised Anomaly Detection with Specified Settings -- 20% anomaly - Metrics: AUC-ROC
Unsupervised Anomaly Detection with Specified Settings -- 30% anomaly - Metrics: AUC-ROC
Unsupervised Anomaly Detection with Specified Settings -- 1% anomaly - Metrics: AUC-ROC
Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomaly - Metrics: AUC-ROC
Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly - Metrics: AUC-ROC

Recent Benchmark Submissions

Task	Model	Paper	Date
Image Clustering	ITAE	Improving Image Clustering with Artifacts …	2024-10-07
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
Self-Supervised Learning	ResNet50	Guarding Barlow Twins Against Overfitting …	2023-12-04
Self-Supervised Learning	ResNet18	Guarding Barlow Twins Against Overfitting …	2023-12-04
Image Generation	RDGAN	A High-Quality Robust Diffusion Framework …	2023-11-28
Image Generation	RDUOT	A High-Quality Robust Diffusion Framework …	2023-11-28
Image Clustering	SeCu	Stable Cluster Discrimination for Deep …	2023-11-24
Image Clustering	TAC	Image Clustering with External Guidance	2023-10-18
Image Clustering	TEMI DINO ViT-B	Exploring the Limits of Deep …	2023-03-31
Image Classification	Diffusion Classifier (zero-shot)	Your Diffusion Model is Secretly …	2023-03-28
Self-Supervised Learning	MV-MR	MV-MR: multi-views and multi-representations for …	2023-03-21
Image Clustering	CoHiClust	Contrastive Hierarchical Clustering	2023-03-03
Image Generation	WaveDiff	Wavelet Diffusion Models are fast …	2022-11-29
Image Clustering	TCL	Twin Contrastive Learning for Online …	2022-10-21
Image Classification	µ2Net+ (ViT-L/16)	A Continual Development Methodology for …	2022-09-15
Image Classification	DLME (ResNet-50, linear)	DLME: Deep Local-flatness Manifold Embedding	2022-07-07
Image Generation	Diffusion ProjectedGAN	Diffusion-GAN: Training GANs with Diffusion	2022-06-05
Image Generation	Diffusion StyleGAN2	Diffusion-GAN: Training GANs with Diffusion	2022-06-05

Research Papers

Recent papers with results on this dataset:

Improving Image Clustering with Artifacts Attenuation via Inference-Time Attention Engineering (2024) -
Deep Online Probability Aggregation Clustering (2024) -
The Balanced-Pairwise-Affinities Feature Transform (2024) -
Let Go of Your Labels with Unsupervised Transfer (2024) -
Guarding Barlow Twins Against Overfitting with Mixed Samples (2023) -
A High-Quality Robust Diffusion Framework for Corrupted Dataset (2023) -
Stable Cluster Discrimination for Deep Clustering (2023) -
Image Clustering with External Guidance (2023) -
Exploring the Limits of Deep Image Clustering using Pretrained Models (2023) -
Your Diffusion Model is Secretly a Zero-Shot Classifier (2023) -
MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation (2023) -
Contrastive Hierarchical Clustering (2023) -
Wavelet Diffusion Models are fast and scalable Image Generators (2022) -
Twin Contrastive Learning for Online Clustering (2022) -
A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems (2022) -
DLME: Deep Local-flatness Manifold Embedding (2022) -
Diffusion-GAN: Training GANs with Diffusion (2022) -
WaveMix: A Resource-efficient Neural Network for Image Analysis (2022) -
Revisiting a kNN-based Image Classification System with High-capacity Storage (2022) -
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision (2022) -

External Links:

STL-10

Overview edit

Associated Benchmarks

Recent Benchmark Submissions

Research Papers

Edit Dataset Information

Overview