# Using Web Co-occurrence Statistics for Improving Image Categorization

arXiv: https://arxiv.org/abs/1312.5697 · HTML: https://mlsanity.com/paper/1312.5697/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2013.

## Built on by (most cited first, 2 of 2)

- [End-to-End Steering for Autonomous Vehicles via Conditional Imitation Co-Learning](https://mlsanity.com/paper/2411.16131/) (2024)
- [Weakly Semi-supervised Tool Detection in Minimally Invasive Surgery Videos](https://mlsanity.com/paper/2401.02791/) (2024)

## Abstract (arXiv)

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.