Deep Association Learning for Unsupervised Video Person Re-identification

2018-08-22 · Yanbei Chen, Xiatian Zhu, Shaogang Gong

Deep learning methods have started to dominate the research progress of video-based person re-identification (re-id). However, existing methods mostly consider supervised learning, which requires exhaustive manual efforts for labelling cross-view pairwise data. Therefore, they severely lack scalability and practicality in real-world video surveillance applications. In this work, to address the video person re-id task, we formulate a novel Deep Association Learning (DAL) scheme, the first end-to-end deep learning method using none of the identity labels in model initialisation and training. DAL learns a deep re-id matching model by jointly optimising two margin-based association losses in an end-to-end manner, which effectively constrains the association of each frame to the best-matched intra-camera representation and cross-camera representation. Existing standard CNNs can be readily employed within our DAL scheme. Experiment results demonstrate that our proposed DAL significantly outperforms current state-of-the-art unsupervised video person re-id methods on three benchmarks: PRID 2011, iLIDS-VID and MARS.

📄 PDF Abstract BibTeX arXiv:1808.07301

Code (1)

yanbeic/Deep-Association-Learning 공식 구현 tf

Tasks

Person Re-Identification Unsupervised Person Re-IdentificationVideo-Based Person Re-Identification

Unsupervised Person Re-identification by Deep Learning Tracklet Association

2018-09-08 · ECCV 2018 9 · Minxian Li, Xiatian Zhu, Shaogang Gong

Mostexistingpersonre-identification(re-id)methods relyon supervised model learning on per-camera-pair manually labelled pairwise training data. This leads to poor scalability in practical re-id deployment due to the lack…

Benchmarking Deep Learning Domain Adaptation Person Re-Identification+1

Unsupervised Graph Association for Person Re-Identification

2019-10-01 · ICCV 2019 10 · Jinlin Wu, Yang Yang, Hao Liu, Shengcai Liao 외

In this paper, we propose an unsupervised graph association (UGA) framework to learn the underlying viewinvariant representations from the video pedestrian tracklets. The core points of UGA are mining the underlying cros…

Domain Adaptation Person Re-Identification

Unsupervised Person Re-Identification with Wireless Positioning under Weak Scene Labeling

2021-10-29 · Yiheng Liu, Wengang Zhou, Qiaokang Xie, Houqiang Li

Existing unsupervised person re-identification methods only rely on visual clues to match pedestrians under different cameras. Since visual data is essentially susceptible to occlusion, blur, clothing changes, etc., a pr…

Graph Neural Network Person Re-Identification Scene Labeling Unsupervised Person Re-Identification

CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions

2020-07-15 · ECCV 2020 8 · Zhongdao Wang, Jingwei Zhang, Liang Zheng, Yixuan Liu 외

This paper proposes a self-supervised learning method for the person re-identification (re-ID) problem, where existing unsupervised methods usually rely on pseudo labels, such as those from video tracklets or clustering.…

Clustering Multi-Object Tracking Object Tracking Person Re-Identification+1

Generalizable Re-Identification from Videos with Cycle Association

2022-11-07 · Zhongdao Wang, Zhaopeng Dou, Jingwei Zhang, Liang Zheng 외

In this paper, we are interested in learning a generalizable person re-identification (re-ID) representation from unlabeled videos. Compared with 1) the popular unsupervised re-ID setting where the training and test sets…

Domain Generalization Generalizable Person Re-identification Person Re-Identification Self-Supervised Learning