# Weakly-supervised Discovery of Visual Pattern Configurations

Source: [Weakly-supervised Discovery of Visual Pattern Configurations](<https://www.sota2.com/research/paper/68fa61691e209131ce9f430e>)

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

Data updated: 2025-10-27T05:48:55.948Z

Authors: Hyun Oh Song, Yong Jae Lee, Stefanie Jegelka, Trevor Darrell

Published: 2014-06-25T09:35:40.000Z

## Abstract

The increasing prominence of weakly labeled data nurtures a growing demand for object detection methods that can cope with minimal supervision. We propose an approach that automatically identifies discriminative configurations of visual patterns that are characteristic of a given object class. We formulate the problem as a constrained submodular optimization problem and demonstrate the benefits of the discovered configurations in remedying mislocalizations and finding informative positive and negative training examples. Together, these lead to state-of-the-art weakly-supervised detection results on the challenging PASCAL VOC dataset.

## 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/1406.6507>)

[PDF](<https://arxiv.org/pdf/1406.6507.pdf>)
