Harvesting Mid-level Visual Concepts from Large-Scale Internet Images

Quannan Li, Jiajun Wu, Zhuowen Tu; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 851-858

Abstract


Obtaining effective mid-level representations has become an increasingly important task in computer vision. In this paper, we propose a fully automatic algorithm which harvests visual concepts from a large number of Internet images (more than a quarter of a million) using text-based queries. Existing approaches to visual concept learning from Internet images either rely on strong supervision with detailed manual annotations or learn image-level classifiers only. Here, we take the advantage of having massive wellorganized Google and Bing image data; visual concepts (around 14, 000) are automatically exploited from images using word-based queries. Using the learned visual concepts, we show state-of-the-art performances on a variety of benchmark datasets, which demonstrate the effectiveness of the learned mid-level representations: being able to generalize well to general natural images. Our method shows significant improvement over the competing systems in image classification, including those with strong supervision.

Related Material


[pdf]
[bibtex]
@InProceedings{Li_2013_CVPR,
author = {Li, Quannan and Wu, Jiajun and Tu, Zhuowen},
title = {Harvesting Mid-level Visual Concepts from Large-Scale Internet Images},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2013}
}