DDRN:a Data Distribution Reconstruction Network for Occluded Person Re-Identification
Not on the map. Why?
Abstract (arXiv)
In occluded person re-identification(ReID), severe occlusions lead to a significant amount of irrelevant information that hinders the accurate identification of individuals. These irrelevant cues primarily stem from background interference and occluding interference, adversely affecting the final retrieval results. Traditional discriminative models, which rely on the specific content and positions of the images, often misclassify in cases of occlusion. To address these limitations, we propose the Data Distribution Reconstruction Network (DDRN), a generative model that leverages data distribution to filter out irrelevant details, enhancing overall feature perception ability and reducing irrelevant feature interference. Additionally, severe occlusions lead to the complexity of the feature space. To effectively handle this, we design a multi-center approach through the proposed Hierarchical SubcenterArcface (HS-Arcface) loss function, which can better approximate complex feature spaces. On the Occluded-Duke dataset, we achieved a mAP of 62.4% (+1.1%) and a rank-1 accuracy of 71.3% (+0.6%), surpassing the latest state-of-the-art methods(FRT) significantly.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 49 of its 69 references that are in the map. First posted on arXiv 9 Oct 2024.
Builds on
49 of 69 references.
References · 49
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2022Generative Adversarial Networkscited by 5,627
- 2017Neural Discrete Representation Learningcited by 4,712
- 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
- 2017Random Erasing Data Augmentationcited by 1,239
- 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 480
- 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 473
- 2021TransReID: Transformer-based Object Re-Identificationcited by 435
- 2019Bag of Tricks and A Strong Baseline for Deep Person Re-identificationcited by 430
- 2018Learning Discriminative Features with Multiple Granularities for Person Re-Identificationcited by 291
- 2017Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitrocited by 281
- 2021Attention Mechanisms in Computer Vision: A Surveycited by 232
37 more
- 2018Harmonious Attention Network for Person Re-Identificationcited by 211
- 2019Relation-Aware Global Attention for Person Re-identificationcited by 124
- 2021Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformercited by 120
- 2020Identity-Guided Human Semantic Parsing for Person Re-Identificationcited by 118
- 2021Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identificationcited by 114
- 2020High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identificationcited by 106
- 2018Human Semantic Parsing for Person Re-identificationcited by 100
- 2017Pose-driven Deep Convolutional Model for Person Re-identificationcited by 86
- 2020AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identificationcited by 81
- 2017A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Rankingcited by 74
- 2018Occluded Person Re-identificationcited by 72
- 2018FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identificationcited by 71
- 2020Pose-guided Visible Part Matching for Occluded Person ReIDcited by 70
- 2022Body Part-Based Representation Learning for Occluded Person Re-Identificationcited by 64
- 2018Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identificationcited by 62
- 2017AlignedReID: Surpassing Human-Level Performance in Person Re-Identificationcited by 61
- 2018Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approachcited by 58
- 2018Multi-Level Factorisation Net for Person Re-Identificationcited by 58
- 2019Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identificationcited by 56
- 2019AANet: Attribute Attention Network for Person Re-Identificationscited by 56
- 2019Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identificationcited by 55
- 2017Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identificationcited by 52
- 2018Person Re-identification with Deep Similarity-Guided Graph Neural Networkcited by 49
- 2021AAformer: Auto-Aligned Transformer for Person Re-Identificationcited by 48
- 2021Combined Depth Space based Architecture Search For Person Re-identificationcited by 44
- 2021Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identificationcited by 44
- 2021Feature Erasing and Diffusion Network for Occluded Person Re-Identificationcited by 42
- 2019Learning Disentangled Representation for Robust Person Re-identificationcited by 40
- 2020Beyond Triplet Loss: Person Re-identification with Fine-grained Difference-aware Pairwise Losscited by 32
- 2022Dynamic Prototype Mask for Occluded Person Re-Identificationcited by 30
- 2019STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identificationcited by 23
- 2018Recognizing Partial Biometric Patternscited by 22
- 2020MHSA-Net: Multi-Head Self-Attention Network for Occluded Person Re-Identificationcited by 13
- 2023Learning Feature Recovery Transformer for Occluded Person Re-identificationcited by 12
- 2021Pose-guided Inter- and Intra-part Relational Transformer for Occluded Person Re-Identificationcited by 11
- 2021Learning to Disentangle Scenes for Person Re-identificationcited by 10
- 2016PersonNet: Person Re-identification with Deep Convolutional Neural Networkscited by 9
Built on by
Not cited yet.