Current approaches to object category recognition require datasets of training images to be manually prepared, with varying degrees of supervision. We present an approach that can learn an object category from just its name, by utilizing the raw output of image search engines available on the Internet. We develop a new model, TSI-pLSA, which extends pLSA (as applied to visual words) to include spatial information in a translation and scale invariant manner. Our approach can handle the high intra-class variability and large proportion of unrelated images returned by search engines. We evaluate tire models on standard test sets, showing performance competitive with existing methods trained on hand prepared datasets.
Learning object categories from Google's image search
Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 ; 2 ; 1816-1823 Vol. 2
2005-01-01
1879371 byte
Conference paper
Electronic Resource
English
Learning Object Categories from Google's Image Search
British Library Conference Proceedings | 2005
|British Library Online Contents | 2009
British Library Online Contents | 2009
Google's Satellite Collection Planning
AIAA | 2016
|Using Google’s Passive Data and Machine Learning for Origin-Destination Demand Estimation
Transportation Research Record | 2018
|