Caltech-256

ImagesUnknown

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

Image Source: ML4A

Benchmarks

Image Classification/Accuracy Semi-Supervised Image Classification/Accuracy

Related Benchmarks

Caltech-256 5-way (1-shot)/Few-Shot Image Classification/Accuracy Caltech-256 5-way (1-shot)/Image Classification/Accuracy Caltech-256 5-way (5-shot)/Few-Shot Image Classification/Accuracy Caltech-256 5-way (5-shot)/Image Classification/Accuracy Caltech-256, 1024 Labels/Image Classification/Accuracy Caltech-256, 1024 Labels/Semi-Supervised Image Classification/Accuracy