AI summary

This paper introduces the Caltech-256 image dataset, a new benchmark for object recognition with 256 categories and 30,607 images, addressing limitations of previous datasets by increasing category count, minimum images per category, and introducing a clutter category for background rejection, demonstrating its challenge through spatial pyramid matching.

Abstract

We introduce a challenging set of 256 object categories containing a total of 30607 images. The original Caltech-101 [1] was collected by choosing a set of object categories, downloading examples from Google Images and then manually screening out all images that did not fit the category. Caltech-256 is collected in a similar manner with several improvement: a) the number of categories is more than doubled, b) the minimum number of images in any category is increased from 31 to 80, c) artifacts due to image rotation are avoided and d) a new and larger clutter category is introduced for testing background rejection. We suggest several testing paradigms to measure classification performance, then benchmark the dataset using two simple metrics as well as a state-of-the-art spatial pyramid matching [2] algorithm. Finally we use the clutter category to train an interest detector which rejects uninformative background regions.