Tiny ImageNet

Introduced by Le et al. in Tiny imagenet visual recognition challenge

Tiny ImageNet contains 100000 images of 200 classes (500 for each class) downsized to 64×64 colored images. Each class has 500 training images, 50 validation images and 50 test images.

Source: Embedded Encoder-Decoder in Convolutional Networks Towards Explainable AI

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Image Classification	Tiny ImageNet Classification	Astroformer
Image Clustering	Tiny-ImageNet	SPICE
Image Classification	Tiny-ImageNet	UPANets
Weakly-Supervised Object Localization	Tiny ImageNet	InfoCAM
Personalized Federated Learning	Tiny ImageNet	SuPerFed-MM
Self-Supervised Learning	Tiny ImageNet	CorInfomax
Clean-label Backdoor Attack (0.05%)	Tiny ImageNet	ResNet-18
Conditional Image Generation	Tiny ImageNet	ADC-GAN