Images

Caltech-101

Introduced by Fei-Fei Li et al. in Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories

The Caltech101 dataset contains images from 101 object categories (e.g., “helicopter”, “elephant” and “chair” etc.) and a background category that contains the images not from the 101 object categories. For each object category, there are about 40 to 800 images, while most classes have about 50 images. The resolution of the image is roughly about 300×200 pixels.

Source: Simple and Efficient Learning using Privileged Information

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Fine-Grained Image Classification	Caltech-101	VIT-L/16
Prompt Engineering	Caltech-101	PromptKD
Density Estimation	Caltech-101	B-NAF
Semantic correspondence	Caltech-101	HPF
Semi-Supervised Image Classification	Caltech-101	UL-Hopfield
Unsupervised Anomaly Detection	Caltech-101	RSRAE
Semi-Supervised Image Classification	Caltech-101, 202 Labels	UL-Hopfield