Caltech-256 Image Dataset
Caltech-256 Dataset is an improved version of Caltech-101 Dataset, with the following main changes:
a) The number of categories more than doubles;
b) the minimum number of images in any category increased from 31 to 80;
c) Avoid artifacts caused by image rotation;
d) A new larger clutter category is introduced to test background rejection.
The dataset contains 20,607 images in 256 categories and was collected by Feifei Li, Marc Andreto, and Marc'Aurelio Ranzato of Caltech.
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.