CGUA: Context-Guided and Unpaired-Assisted Weakly Supervised Person Search
Not on the map. Why?
Abstract (arXiv)
Recently, weakly supervised person search is proposed to discard human-annotated identities and train the model with only bounding box annotations. A natural way to solve this problem is to separate it into detection and unsupervised re-identification (Re-ID) steps. However, in this way, two important clues in unconstrained scene images are ignored. On the one hand, existing unsupervised Re-ID models only leverage cropped images from scene images but ignore its rich context information. On the other hand, there are numerous unpaired persons in real-world scene images. Directly dealing with them as independent identities leads to the long-tail effect, while completely discarding them can result in serious information loss. In light of these challenges, we introduce a Context-Guided and Unpaired-Assisted (CGUA) weakly supervised person search framework. Specifically, we propose a novel Context-Guided Cluster (CGC) algorithm to leverage context information in the clustering process and an Unpaired-Assisted Memory (UAM) unit to distinguish unpaired and paired persons by pushing them away. Extensive experiments demonstrate that the proposed approach can surpass the state-of-the-art weakly supervised methods by a large margin (more than 5% mAP on CUHK-SYSU). Moreover, our method achieves comparable or better performance to the state-of-the-art supervised methods by leveraging more diverse unlabeled data. Codes and models will be released soon.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 21 of its 33 references that are in the map. First posted on arXiv 27 Mar 2022.
Builds on
21 of 33 references.
References · 21
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2016Feature Pyramid Networks for Object Detectioncited by 5,021
- 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 497
- 2020Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-IDcited by 212
- 2016Joint Detection and Identification Feature Learning for Person Searchcited by 190
- 2020Unsupervised Person Re-identification via Multi-label Classificationcited by 107
- 2019Efficient Parameter-free Clustering Using First Neighbor Relationscited by 96
- 2021Cluster Contrast for Unsupervised Person Re-Identificationcited by 89
- 2019Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identificationcited by 83
- 2019Learning Context Graph for Person Searchcited by 55
- 2018Person Search via A Mask-Guided Two-Stream CNN Modelcited by 44
9 more
- 2021Anchor-Free Person Searchcited by 42
- 2019Re-ID Driven Localization Refinement for Person Searchcited by 41
- 2021Sequential End-to-end Network for Efficient Person Searchcited by 38
- 2018Person Search by Multi-Scale Matchingcited by 36
- 2020Diverse Knowledge Distillation for End-to-End Person Searchcited by 16
- 2021Exploring Visual Context for Weakly Supervised Person Searchcited by 16
- 2021Weakly Supervised Person Search with Region Siamese Networkscited by 14
- 2021Hard-sample Guided Hybrid Contrast Learning for Unsupervised Person Re-Identificationcited by 12
- 2021Context-Aware Unsupervised Clustering for Person Searchcited by 6
Built on by
Citing papers per year: 2023: 3.
3 papers.