# Feature Erasing and Diffusion Network for Occluded Person Re-Identification

arXiv: https://arxiv.org/abs/2112.08740 · HTML: https://mlsanity.com/paper/2112.08740/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 43 references that are in the map.
- First posted on arXiv 16 Dec 2021.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [On Layer Normalization in the Transformer Architecture](https://mlsanity.com/paper/2002.04745/) (2020)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID](https://mlsanity.com/paper/2006.02713/) (2020)
- [Harmonious Attention Network for Person Re-Identification](https://mlsanity.com/paper/1802.08122/) (2018)
- [Beyond triplet loss: a deep quadruplet network for person re-identification](https://mlsanity.com/paper/1704.01719/) (2017)
- [Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer](https://mlsanity.com/paper/2106.04095/) (2021)
- [High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification](https://mlsanity.com/paper/2003.08177/) (2020)
- [Occluded Person Re-identification](https://mlsanity.com/paper/1804.02792/) (2018)
- [FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification](https://mlsanity.com/paper/1810.02936/) (2018)
- [Pose-guided Visible Part Matching for Occluded Person ReID](https://mlsanity.com/paper/2004.00230/) (2020)
- [AlignedReID: Surpassing Human-Level Performance in Person Re-Identification](https://mlsanity.com/paper/1711.08184/) (2017)
- [Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach](https://mlsanity.com/paper/1801.00881/) (2018)
- [AANet: Attribute Attention Network for Person Re-Identifications](https://mlsanity.com/paper/1912.09021/) (2019)
- [Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification](https://mlsanity.com/paper/1904.04975/) (2019)
- [Attention-Aware Compositional Network for Person Re-identification](https://mlsanity.com/paper/1805.03344/) (2018)
- [Recognizing Partial Biometric Patterns](https://mlsanity.com/paper/1810.07399/) (2018)
- [Attention Driven Person Re-identification](https://mlsanity.com/paper/1810.05866/) (2018)

## Built on by (most cited first, 30 of 42)

- [Body Part-Based Representation Learning for Occluded Person Re-Identification](https://mlsanity.com/paper/2211.03679/) (2022)
- [Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions](https://mlsanity.com/paper/2306.07520/) (2023)
- [Region Generation and Assessment Network for Occluded Person Re-Identification](https://mlsanity.com/paper/2309.03558/) (2023)
- [AG-ReID.v2: Bridging Aerial and Ground Views for Person Re-identification](https://mlsanity.com/paper/2401.02634/) (2024)
- [Aerial-Ground Person Re-ID](https://mlsanity.com/paper/2303.08597/) (2023)
- [Erasing, Transforming, and Noising Defense Network for Occluded Person Re-Identification](https://mlsanity.com/paper/2307.07187/) (2023)
- [From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization](https://mlsanity.com/paper/2503.00938/) (2025)
- [Multi-view Information Integration and Propagation for Occluded Person Re-identification](https://mlsanity.com/paper/2311.03828/) (2023)
- [Keypoint Promptable Re-Identification](https://mlsanity.com/paper/2407.18112/) (2024)
- [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)
- [Deep Learning-based Occluded Person Re-identification: A Survey](https://mlsanity.com/paper/2207.14452/) (2022)
- [Exploring Fine-Grained Representation and Recomposition for Cloth-Changing Person Re-Identification](https://mlsanity.com/paper/2308.10692/) (2023)
- [Feature Completion Transformer for Occluded Person Re-identification](https://mlsanity.com/paper/2303.01656/) (2023)
- [Unity is Strength: Unifying Convolutional and Transformeral Features for Better Person Re-Identification](https://mlsanity.com/paper/2412.17239/) (2024)
- [ICPL-ReID: Identity-Conditional Prompt Learning for Multi-Spectral Object Re-Identification](https://mlsanity.com/paper/2505.17821/) (2025)
- [Dynamic Feature Pruning and Consolidation for Occluded Person Re-Identification](https://mlsanity.com/paper/2211.14742/) (2022)
- [SD-ReID: View-aware Stable Diffusion for Aerial-Ground Person Re-Identification](https://mlsanity.com/paper/2504.09549/) (2025)
- [Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-identification](https://mlsanity.com/paper/2303.10976/) (2023)
- [PersonMAE: Person Re-Identification Pre-Training with Masked AutoEncoders](https://mlsanity.com/paper/2311.04496/) (2023)
- [Parallel Augmentation and Dual Enhancement for Occluded Person Re-identification](https://mlsanity.com/paper/2210.05438/) (2022)
- [Part-Attention Based Model Make Occluded Person Re-Identification Stronger](https://mlsanity.com/paper/2404.03443/) (2024)
- [TransitReID: Transit OD Data Collection with Occlusion-Resistant Dynamic Passenger Re-Identification](https://mlsanity.com/paper/2504.11500/) (2025)
- [Part Representation Learning with Teacher-Student Decoder for Occluded Person Re-identification](https://mlsanity.com/paper/2312.09797/) (2023)
- [Exploring Stronger Transformer Representation Learning for Occluded Person Re-Identification](https://mlsanity.com/paper/2410.15613/) (2024)
- ["Reading Between the Heat": Co-Teaching Body Thermal Signatures for Non-intrusive Stress Detection](https://mlsanity.com/paper/2310.09932/) (2023)
- [Dynamic Patch-aware Enrichment Transformer for Occluded Person Re-Identification](https://mlsanity.com/paper/2402.10435/) (2024)
- [CityGuard: Graph-Aware Private Descriptors for Bias-Resilient Identity Search Across Urban Cameras](https://mlsanity.com/paper/2602.18047/) (2026)
- [Multiplex-detection Based Multiple Instance Learning Network for Whole Slide Image Classification](https://mlsanity.com/paper/2208.03526/) (2022)
- [DaliID: Distortion-Adaptive Learned Invariance for Identification Models](https://mlsanity.com/paper/2302.05753/) (2023)

## Abstract (arXiv)

Occluded person re-identification (ReID) aims at matching occluded person images to holistic ones across different camera views. Target Pedestrians (TP) are usually disturbed by Non-Pedestrian Occlusions (NPO) and NonTarget Pedestrians (NTP). Previous methods mainly focus on increasing model's robustness against NPO while ignoring feature contamination from NTP. In this paper, we propose a novel Feature Erasing and Diffusion Network (FED) to simultaneously handle NPO and NTP. Specifically, NPO features are eliminated by our proposed Occlusion Erasing Module (OEM), aided by the NPO augmentation strategy which simulates NPO on holistic pedestrian images and generates precise occlusion masks. Subsequently, we Subsequently, we diffuse the pedestrian representations with other memorized features to synthesize NTP characteristics in the feature space which is achieved by a novel Feature Diffusion Module (FDM) through a learnable cross attention mechanism. With the guidance of the occlusion scores from OEM, the feature diffusion process is mainly conducted on visible body parts, which guarantees the quality of the synthesized NTP characteristics. By jointly optimizing OEM and FDM in our proposed FED network, we can greatly improve the model's perception ability towards TP and alleviate the influence of NPO and NTP. Furthermore, the proposed FDM only works as an auxiliary module for training and will be discarded in the inference phase, thus introducing little inference computational overhead. Experiments on occluded and holistic person ReID benchmarks demonstrate the superiority of FED over state-of-the-arts, where FED achieves 86.3% Rank-1 accuracy on Occluded-REID, surpassing others by at least 4.7%.