# Holistic Guidance for Occluded Person Re-Identification

arXiv: https://arxiv.org/abs/2104.06524 · HTML: https://mlsanity.com/paper/2104.06524/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 59 references that are in the map.
- First posted on arXiv 13 Apr 2021.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net](https://mlsanity.com/paper/1807.09441/) (2018)
- [Joint Discriminative and Generative Learning for Person Re-identification](https://mlsanity.com/paper/1904.07223/) (2019)
- [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)
- [High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification](https://mlsanity.com/paper/2003.08177/) (2020)
- [Human Semantic Parsing for Person Re-identification](https://mlsanity.com/paper/1804.00216/) (2018)
- [Part-Aligned Bilinear Representations for Person Re-identification](https://mlsanity.com/paper/1804.07094/) (2018)
- [Pose-driven Deep Convolutional Model for Person Re-identification](https://mlsanity.com/paper/1709.08325/) (2017)
- [Occluded Person Re-identification](https://mlsanity.com/paper/1804.02792/) (2018)
- [Pose-guided Visible Part Matching for Occluded Person ReID](https://mlsanity.com/paper/2004.00230/) (2020)
- [Deeply-Learned Part-Aligned Representations for Person Re-Identification](https://mlsanity.com/paper/1707.07256/) (2017)
- [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)
- [Multi-Level Factorisation Net for Person Re-Identification](https://mlsanity.com/paper/1803.09132/) (2018)
- [Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd](https://mlsanity.com/paper/1807.08407/) (2018)
- [Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification](https://mlsanity.com/paper/1904.04975/) (2019)
- [Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification](https://mlsanity.com/paper/1710.06555/) (2017)
- [Pose Invariant Embedding for Deep Person Re-identification](https://mlsanity.com/paper/1701.07732/) (2017)
- [End-to-End Comparative Attention Networks for Person Re-identification](https://mlsanity.com/paper/1606.04404/) (2016)
- [Gated Siamese Convolutional Neural Network Architecture for Human Re-Identification](https://mlsanity.com/paper/1607.08378/) (2016)
- [Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification](https://mlsanity.com/paper/2007.13890/) (2020)
- [GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval](https://mlsanity.com/paper/1709.04329/) (2017)
- [Learning a Discriminative Null Space for Person Re-identification](https://mlsanity.com/paper/1603.02139/) (2016)
- [Recognizing Partial Biometric Patterns](https://mlsanity.com/paper/1810.07399/) (2018)
- [A Novel Teacher-Student Learning Framework For Occluded Person Re-Identification](https://mlsanity.com/paper/1907.03253/) (2019)

## Built on by (most cited first, 9 of 9)

- [Body Part-Based Representation Learning for Occluded Person Re-Identification](https://mlsanity.com/paper/2211.03679/) (2022)
- [Erasing, Transforming, and Noising Defense Network for Occluded Person Re-Identification](https://mlsanity.com/paper/2307.07187/) (2023)
- [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)
- [Occluded Person Re-Identification with Deep Learning: A Survey and Perspectives](https://mlsanity.com/paper/2311.00603/) (2023)
- [Visible-Infrared Person Re-Identification Using Privileged Intermediate Information](https://mlsanity.com/paper/2209.09348/) (2022)
- [Learning Comprehensive Representations with Richer Self for Text-to-Image Person Re-Identification](https://mlsanity.com/paper/2310.11210/) (2023)
- [Enhancing person re-identification via Uncertainty Feature Fusion Method and Auto-weighted Measure Combination](https://mlsanity.com/paper/2405.01101/) (2024)
- [Part-Attention Based Model Make Occluded Person Re-Identification Stronger](https://mlsanity.com/paper/2404.03443/) (2024)

## Abstract (arXiv)

In real-world video surveillance applications, person re-identification (ReID) suffers from the effects of occlusions and detection errors. Despite recent advances, occlusions continue to corrupt the features extracted by state-of-art CNN backbones, and thereby deteriorate the accuracy of ReID systems. To address this issue, methods in the literature use an additional costly process such as pose estimation, where pose maps provide supervision to exclude occluded regions. In contrast, we introduce a novel Holistic Guidance (HG) method that relies only on person identity labels, and on the distribution of pairwise matching distances of datasets to alleviate the problem of occlusion, without requiring additional supervision. Hence, our proposed student-teacher framework is trained to address the occlusion problem by matching the distributions of between- and within-class distances (DCDs) of occluded samples with that of holistic (non-occluded) samples, thereby using the latter as a soft labeled reference to learn well separated DCDs. This approach is supported by our empirical study where the distribution of between- and within-class distances between images have more overlap in occluded than holistic datasets. In particular, features extracted from both datasets are jointly learned using the student model to produce an attention map that allows separating visible regions from occluded ones. In addition to this, a joint generative-discriminative backbone is trained with a denoising autoencoder, allowing the system to self-recover from occlusions. Extensive experiments on several challenging public datasets indicate that the proposed approach can outperform state-of-the-art methods on both occluded and holistic datasets