The human visual system is remarkably tolerant to degradations in image resolution: in a scene recognition task, human performance is similar whether $32 \times 32$ color images or multi-mega pixel images are used. With small images, even object recognition and segmentation is performed robustly by the visual system, despite the object being unrecognizable in isolation. Motivated by these observations, we explore the space of 32x32 images using a database of 10^8 32x32 color images gathered from the Internet using image search engines. Each image is loosely labeled with one of the 70,399 non-abstract nouns in English, as listed in the Wordnet lexical database. Hence the image database represents a dense sampling of all object categories and scenes. With this dataset, we use nearest neighbor methods to perform objectrecognition across the 10^8 images.


    Access

    Download


    Export, share and cite



    Title :

    Tiny images


    Contributors:

    Publication date :

    2007


    Size :

    9 pages


    Type of media :

    Miscellaneous


    Type of material :

    Electronic Resource


    Language :

    Unknown




    Visual self-localization with tiny images

    Hofmeister, Marius / Erhard, Sara / Zell, Andreas | Tema Archive | 2009


    Tiny solar cells power tiny MEMS machines

    British Library Online Contents | 2009


    Tiny turbochargers

    Hartley,J. / Mitsubishi,JP | Automotive engineering | 1981


    Schweizerisch:das Klappauto Tiny

    Stoop,M. | Automotive engineering | 1995


    Tiny CAN Monitor

    Emaus, Bruce | SAE Technical Papers | 2000