# Occluded Person Re-Identification via Relational Adaptive Feature Correction Learning

arXiv: https://arxiv.org/abs/2212.04712 · HTML: https://mlsanity.com/paper/2212.04712/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 18 references that are in the map.
- First posted on arXiv 9 Dec 2022.

## Builds on (most cited first, 12 of 12)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [A simple neural network module for relational reasoning](https://mlsanity.com/paper/1706.01427/) (2017)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer](https://mlsanity.com/paper/2106.04095/) (2021)
- [Identity-Guided Human Semantic Parsing for Person Re-Identification](https://mlsanity.com/paper/2007.13467/) (2020)
- [High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification](https://mlsanity.com/paper/2003.08177/) (2020)
- [Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification](https://mlsanity.com/paper/1904.04975/) (2019)
- [Re-Identification with Consistent Attentive Siamese Networks](https://mlsanity.com/paper/1811.07487/) (2018)
- [Relation Network for Person Re-identification](https://mlsanity.com/paper/1911.09318/) (2019)
- [Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians](https://mlsanity.com/paper/2008.06963/) (2020)

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

- [Occluded Person Re-Identification with Deep Learning: A Survey and Perspectives](https://mlsanity.com/paper/2311.00603/) (2023)
- [Feature Disentanglement Learning with Switching and Aggregation for Video-based Person Re-Identification](https://mlsanity.com/paper/2212.09498/) (2022)
- [Background Matters Too: A Language-Enhanced Adversarial Framework for Person Re-Identification](https://mlsanity.com/paper/2509.03032/) (2025)
- [QA-ReID: Quality-Aware Query-Adaptive Convolution Leveraging Fused Global and Structural Cues for Clothes-Changing ReID](https://mlsanity.com/paper/2601.19133/) (2026)

## Abstract (arXiv)

Occluded person re-identification (Re-ID) in images captured by multiple cameras is challenging because the target person is occluded by pedestrians or objects, especially in crowded scenes. In addition to the processes performed during holistic person Re-ID, occluded person Re-ID involves the removal of obstacles and the detection of partially visible body parts. Most existing methods utilize the off-the-shelf pose or parsing networks as pseudo labels, which are prone to error. To address these issues, we propose a novel Occlusion Correction Network (OCNet) that corrects features through relational-weight learning and obtains diverse and representative features without using external networks. In addition, we present a simple concept of a center feature in order to provide an intuitive solution to pedestrian occlusion scenarios. Furthermore, we suggest the idea of Separation Loss (SL) for focusing on different parts between global features and part features. We conduct extensive experiments on five challenging benchmark datasets for occluded and holistic Re-ID tasks to demonstrate that our method achieves superior performance to state-of-the-art methods especially on occluded scene.