# Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond

arXiv: https://arxiv.org/abs/2002.09274 · HTML: https://mlsanity.com/paper/2002.09274/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2020.

## Built on by (most cited first, 4 of 4)

- [Deep High-Resolution Representation Learning for Cross-Resolution Person Re-identification](https://mlsanity.com/paper/2105.11722/) (2021)
- [Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identification](https://mlsanity.com/paper/2207.13037/) (2022)
- [Pluggable Weakly-Supervised Cross-View Learning for Accurate Vehicle Re-Identification](https://mlsanity.com/paper/2103.05376/) (2021)
- [Center Prediction Loss for Re-identification](https://mlsanity.com/paper/2104.14746/) (2021)

## Abstract (arXiv)

Person re-identification (re-ID) aims at matching images of the same person across camera views. Due to varying distances between cameras and persons of interest, resolution mismatch can be expected, which would degrade re-ID performance in real-world scenarios. To overcome this problem, we propose a novel generative adversarial network to address cross-resolution person re-ID, allowing query images with varying resolutions. By advancing adversarial learning techniques, our proposed model learns resolution-invariant image representations while being able to recover the missing details in low-resolution input images. The resulting features can be jointly applied for improving re-ID performance due to preserving resolution invariance and recovering re-ID oriented discriminative details. Extensive experimental results on five standard person re-ID benchmarks confirm the effectiveness of our method and the superiority over the state-of-the-art approaches, especially when the input resolutions are not seen during training. Furthermore, the experimental results on two vehicle re-ID benchmarks also confirm the generalization of our model on cross-resolution visual tasks. The extensions of semi-supervised settings further support the use of our proposed approach to real-world scenarios and applications.