# Automatic discovery of discriminative parts as a quadratic assignment problem

Source: [Automatic discovery of discriminative parts as a quadratic assignment problem](<https://www.sota2.com/research/paper/68fa62d81e209131ce9fb8d6>)

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

Data updated: 2025-10-25T20:28:18.594Z

Authors: Ronan Sicre, Julien Rabin, Yannis Avrithis, Teddy Furon, Frederic Jurie

Published: 2016-11-14T15:17:48.000Z

## Abstract

Part-based image classification consists in representing categories by small sets of discriminative parts upon which a representation of the images is built. This paper addresses the question of how to automatically learn such parts from a set of labeled training images. The training of parts is cast as a quadratic assignment problem in which optimal correspondences between image regions and parts are automatically learned. The paper analyses different assignment strategies and thoroughly evaluates them on two public datasets: Willow actions and MIT 67 scenes. State-of-the art results are obtained on these 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/1611.04413>)

[PDF](<https://arxiv.org/pdf/1611.04413.pdf>)