# Using Web Co-occurrence Statistics for Improving Image Categorization

Source: [Using Web Co-occurrence Statistics for Improving Image Categorization](<https://www.sota2.com/research/paper/68fa61291e209131ce9f2d3a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T19:53:34.667Z

Authors: Samy Bengio, Jeff Dean, Dumitru Erhan, Eugene Ie, Quoc Le, Andrew Rabinovich, Jonathon Shlens, Yoram Singer

Published: 2013-12-19T18:53:47.000Z

## Abstract

Object recognition and localization are important tasks in computer vision. The focus of this work is the incorporation of contextual information in order to improve object recognition and localization. For instance, it is natural to expect not to see an elephant to appear in the middle of an ocean. We consider a simple approach to encapsulate such common sense knowledge using co-occurrence statistics from web documents. By merely counting the number of times nouns (such as elephants, sharks, oceans, etc.) co-occur in web documents, we obtain a good estimate of expected co-occurrences in visual data. We then cast the problem of combining textual co-occurrence statistics with the predictions of image-based classifiers as an optimization problem. The resulting optimization problem serves as a surrogate for our inference procedure. Albeit the simplicity of the resulting optimization problem, it is effective in improving both recognition and localization accuracy. Concretely, we observe significant improvements in recognition and localization rates for both ImageNet Detection 2012 and Sun 2012 datasets.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1312.5697>)

[PDF](<https://arxiv.org/pdf/1312.5697.pdf>)
