# Iterative Projection and Matching: Finding Structure-preserving Representatives and Its Application to Computer Vision

arXiv: https://arxiv.org/abs/1811.12326 · HTML: https://mlsanity.com/paper/1811.12326/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2018.

## Built on by (most cited first, 6 of 6)

- [Improving Replay Sample Selection and Storage for Less Forgetting in Continual Learning](https://mlsanity.com/paper/2308.01895/) (2023)
- [Predicting the Susceptibility of Examples to Catastrophic Forgetting](https://mlsanity.com/paper/2406.09935/) (2024)
- [Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation](https://mlsanity.com/paper/2207.09280/) (2022)
- [GUIDE: Guidance-based Incremental Learning with Diffusion Models](https://mlsanity.com/paper/2403.03938/) (2024)
- [Two-way Spectrum Pursuit for CUR Decomposition and Its Application in Joint Column/Row Subset Selection](https://mlsanity.com/paper/2106.06983/) (2021)
- [Task-Focused Consolidation with Spaced Recall: Making Neural Networks Learn like College Students](https://mlsanity.com/paper/2507.21109/) (2025)

## Abstract (arXiv)

The goal of data selection is to capture the most structural information from a set of data. This paper presents a fast and accurate data selection method, in which the selected samples are optimized to span the subspace of all data. We propose a new selection algorithm, referred to as iterative projection and matching (IPM), with linear complexity w.r.t. the number of data, and without any parameter to be tuned. In our algorithm, at each iteration, the maximum information from the structure of the data is captured by one selected sample, and the captured information is neglected in the next iterations by projection on the null-space of previously selected samples. The computational efficiency and the selection accuracy of our proposed algorithm outperform those of the conventional methods. Furthermore, the superiority of the proposed algorithm is shown on active learning for video action recognition dataset on UCF-101; learning using representatives on ImageNet; training a generative adversarial network (GAN) to generate multi-view images from a single-view input on CMU Multi-PIE dataset; and video summarization on UTE Egocentric dataset.