# Automatic discovery of discriminative parts as a quadratic assignment problem

arXiv: https://arxiv.org/abs/1611.04413 · HTML: https://mlsanity.com/paper/1611.04413/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Nov 2016.

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

- [VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning](https://mlsanity.com/paper/2203.10444/) (2022)
- [DP-Net: Learning Discriminative Parts for image recognition](https://mlsanity.com/paper/2404.15037/) (2024)

## Abstract (arXiv)

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.