# Resolution-invariant Person ReID Based on Feature Transformation and Self-weighted Attention

arXiv: https://arxiv.org/abs/2101.04544 · HTML: https://mlsanity.com/paper/2101.04544/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 12 Jan 2021.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [Lightweight Image Super-Resolution with Information Multi-distillation Network](https://mlsanity.com/paper/1909.11856/) (2019)
- [Joint Discriminative and Generative Learning for Person Re-identification](https://mlsanity.com/paper/1904.07223/) (2019)
- [Person Re-identification: Past, Present and Future](https://mlsanity.com/paper/1610.02984/) (2016)
- [Progressive Pose Attention Transfer for Person Image Generation](https://mlsanity.com/paper/1904.03349/) (2019)
- [Pose-Normalized Image Generation for Person Re-identification](https://mlsanity.com/paper/1712.02225/) (2017)
- [Multi-Level Factorisation Net for Person Re-Identification](https://mlsanity.com/paper/1803.09132/) (2018)
- [VRSTC: Occlusion-Free Video Person Re-Identification](https://mlsanity.com/paper/1907.08427/) (2019)
- [Illumination-Adaptive Person Re-identification](https://mlsanity.com/paper/1905.04525/) (2019)
- [Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification](https://mlsanity.com/paper/1908.06052/) (2019)
- [Learning Resolution-Invariant Deep Representations for Person Re-Identification](https://mlsanity.com/paper/1907.10843/) (2019)
- [Resolution-invariant Person Re-Identification](https://mlsanity.com/paper/1906.09748/) (2019)
- [Illumination adaptive person reid based on teacher-student model and adversarial training](https://mlsanity.com/paper/2002.01625/) (2020)

## Built on by (most cited first, 1 of 1)

- [A Versatile Framework for Multi-scene Person Re-identification](https://mlsanity.com/paper/2403.11121/) (2024)

## Abstract (arXiv)

Person Re-identification (ReID) is a critical computer vision task which aims to match the same person in images or video sequences. Most current works focus on settings where the resolution of images is kept the same. However, the resolution is a crucial factor in person ReID, especially when the cameras are at different distances from the person or the camera's models are different from each other. In this paper, we propose a novel two-stream network with a lightweight resolution association ReID feature transformation (RAFT) module and a self-weighted attention (SWA) ReID module to evaluate features under different resolutions. RAFT transforms the low resolution features to corresponding high resolution features. SWA evaluates both features to get weight factors for the person ReID. Both modules are jointly trained to get a resolution-invariant representation. Extensive experiments on five benchmark datasets show the effectiveness of our method. For instance, we achieve Rank-1 accuracy of 43.3% and 83.2% on CAVIAR and MLR-CUHK03, outperforming the state-of-the-art.