Caltech-256

Introduced by Griffin et al. in Caltech-256 object category dataset

Caltech-256 is an object recognition dataset containing 30,607 real-world images, of different sizes, spanning 257 classes (256 object classes and an additional clutter class). Each class is represented by at least 80 images. The dataset is a superset of the Caltech-101 dataset.

Source: Exploiting Non-Linear Redundancy for Neural Model Compression

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Image Classification	Caltech-256	AG-Net
Few-Shot Image Classification	Caltech-256 5-way (1-shot)	UL-Hopfield
Semi-Supervised Image Classification	Caltech-256, 1024 Labels	UL-Hopfield
Semi-Supervised Image Classification	Caltech-256	UL-Hopfield