# Resolution-invariant Person Re-Identification

arXiv: https://arxiv.org/abs/1906.09748 · HTML: https://mlsanity.com/paper/1906.09748/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2019.

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

- [Deep learning-based person re-identification methods: A survey and outlook of recent works](https://mlsanity.com/paper/2110.04764/) (2021)
- [Deep High-Resolution Representation Learning for Cross-Resolution Person Re-identification](https://mlsanity.com/paper/2105.11722/) (2021)
- [A Versatile Framework for Multi-scene Person Re-identification](https://mlsanity.com/paper/2403.11121/) (2024)
- [Occluded Person Re-Identification with Deep Learning: A Survey and Perspectives](https://mlsanity.com/paper/2311.00603/) (2023)
- [Low Resolution Information Also Matters: Learning Multi-Resolution Representations for Person Re-Identification](https://mlsanity.com/paper/2105.12684/) (2021)
- [Resolution-invariant Person ReID Based on Feature Transformation and Self-weighted Attention](https://mlsanity.com/paper/2101.04544/) (2021)

## Abstract (arXiv)

Exploiting resolution invariant representation is critical for person Re-Identification (ReID) in real applications, where the resolutions of captured person images may vary dramatically. This paper learns person representations robust to resolution variance through jointly training a Foreground-Focus Super-Resolution (FFSR) module and a Resolution-Invariant Feature Extractor (RIFE) by end-to-end CNN learning. FFSR upscales the person foreground using a fully convolutional auto-encoder with skip connections learned with a foreground focus training loss. RIFE adopts two feature extraction streams weighted by a dual-attention block to learn features for low and high resolution images, respectively. These two complementary modules are jointly trained, leading to a strong resolution invariant representation. We evaluate our methods on five datasets containing person images at a large range of resolutions, where our methods show substantial superiority to existing solutions. For instance, we achieve Rank-1 accuracy of 36.4% and 73.3% on CAVIAR and MLR-CUHK03, outperforming the state-of-the art by 2.9% and 2.6%, respectively.