# Cross-View Asymmetric Metric Learning for Unsupervised Person Re-Identification

@article{Yu2017CrossViewAM,
title={Cross-View Asymmetric Metric Learning for Unsupervised Person Re-Identification},
author={Hong-Xing Yu and Ancong Wu and Weishi Zheng},
journal={2017 IEEE International Conference on Computer Vision (ICCV)},
year={2017},
pages={994-1002}
}
• Published 27 August 2017
• Computer Science
• 2017 IEEE International Conference on Computer Vision (ICCV)
While metric learning is important for Person reidentification (RE-ID), a significant problem in visual surveillance for cross-view pedestrian matching, existing metric models for RE-ID are mostly based on supervised learning that requires quantities of labeled samples in all pairs of camera views for training. However, this limits their scalabilities to realistic applications, in which a large amount of data over multiple disjoint camera views is available but not labelled. To overcome the…
257 Citations

## Figures and Tables from this paper

Unsupervised Person Re-Identification by Deep Asymmetric Metric Embedding
• Computer Science
IEEE Transactions on Pattern Analysis and Machine Intelligence
• 2020
A novel unsupervised deep framework named the DEep Clustering-based Asymmetric MEtric Learning (DECAMEL) is developed, which learns a compact cross-view cluster structure of Re-ID data to help alleviate the view-specific bias and facilitate mining the potential cross-View discriminative information for unsuper supervised Re- ID.
Unsupervised Person Re-Identification by Camera-Aware Similarity Consistency Learning
• Computer Science
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
• 2019
A coarse-to-fine consistency learning scheme to learn consistency globally and locally in two steps to avoid learning ineffective knowledge in consistency learning and preserve the prior common knowledge of intra-camera matching in the pretrained model as reliable guiding information, which does not suffer from cross-camera scene variation as cross- camera matching.
Person Reidentification via Unsupervised Cross-View Metric Learning
• Computer Science
IEEE Transactions on Cybernetics
• 2021
An unsupervised cross-view metric learning method based on the properties of data distributions for person reidentification, which learns view-specific mappings to extract and project view-related features into a common subspace.
Cross-view pedestrian clustering via graph convolution network for unsupervised person re-identification
• Computer Science
J. Intell. Fuzzy Syst.
• 2020
The proposed unsupervised person re-identification metric learning method learns a shared space to reduce the discrepancy under different cameras, and improves the scalability of pedestrian re-Identification in practical application scenarios.
Distilled Camera-Aware Self Training for Semi-Supervised Person Re-Identification
• Computer Science
IEEE Access
• 2019
A Distilled Camera-Aware Self Training framework for semi-supervised person re-identification, and a Multi-Teacher Selective Similarity Distillation Loss to selectively aggregate the knowledge of multiple weak teacher models trained with different subsets and distill a stronger student model for self training.
Cluster-Guided Asymmetric Contrastive Learning for Unsupervised Person Re-Identification
• Computer Science
IEEE Transactions on Image Processing
• 2022
This paper proposes a Cluster-guided Asymmetric Contrastive Learning (CACL) approach for unsupervised person Re-ID, in which clustering result is leveraged to guide the feature learning in a properly designed asymmetric contrastive learning framework.
Semi-supervised Region Metric Learning for Person Re-identification
• Computer Science
International Journal of Computer Vision
• 2018
A novel semi-supervised region metric learning method to improve person re-identification performance under imbalanced unlabeled data is proposed, which proposes to estimate positive neighbors by label propagation with cross person score distribution alignment.
View-Invariant and Similarity Learning for Robust Person Re-Identification
• Computer Science
IEEE Access
• 2019
It is shown that the problem of the large variation in viewpoints of a pedestrian can be well solved using a multi-view network and an adaptive similarity loss function to better learn a similarity metric is proposed.
Domain-Aware Unsupervised Cross-dataset Person Re-identification
• Computer Science
• 2019
This paper proposes a novel domain-aware representation learning algorithm that not only learns a common appearances across-datasets but also captures the domain-unique appearances on the target dataset via minimization of the overlapped signal supports across different domains.

## References

SHOWING 1-10 OF 38 REFERENCES
Cross-Scenario Transfer Person Reidentification
• Computer Science
IEEE Transactions on Circuits and Systems for Video Technology
• 2016
The proposed method, called the constrained asymmetric multitask discriminant component analysis (cAMT-DCA), can be solved by a simple eigen decomposition with a closed form, getting rid of any iterative learning used in most conventional MTL analyses.
Person Re-Identification by Unsupervised \ell _1 ℓ 1 Graph Learning
• Computer Science
ECCV
• 2016
This work proposes a novel unsupervised Re-ID approach which requires no labelled training data yet is able to capture discriminative information for cross-view identity matching, and is based on a new graph regularised dictionary learning algorithm.
An Asymmetric Distance Model for Cross-View Feature Mapping in Person Reidentification
• Computer Science
IEEE Transactions on Circuits and Systems for Video Technology
• 2017
An asymmetric distance model for learning camera-specific projections to transform the unmatched features of each view into a common space where discriminative features across view space are extracted, and a cross-view consistency regularization is introduced.
Dictionary Learning with Iterative Laplacian Regularisation for Unsupervised Person Re-identification
• Computer Science
BMVC
• 2015
A new dictionary learning for sparse coding formulation with a graph Laplacian regularisation term whose value is set iteratively enables the exploitation of cross-view identity-discriminative information ignored by existing unsupervised Re-ID methods.
Efficient PSD Constrained Asymmetric Metric Learning for Person Re-Identification
• Computer Science
2015 IEEE International Conference on Computer Vision (ICCV)
• 2015
A logistic metric learning approach with the PSD constraint and an asymmetric sample weighting strategy is derived, achieving state-of-the-art performance on four challenging databases and compared to existing metric learning methods as well as published results.
Scalable Person Re-identification: A Benchmark
• Computer Science
2015 IEEE International Conference on Computer Vision (ICCV)
• 2015
A minor contribution, inspired by recent advances in large-scale image search, an unsupervised Bag-of-Words descriptor is proposed that yields competitive accuracy on VIPeR, CUHK03, and Market-1501 datasets, and is scalable on the large- scale 500k dataset.
Towards unsupervised open-set person re-identification
• Computer Science
2016 IEEE International Conference on Image Processing (ICIP)
• 2016
This work introduces a more challenging yet realistic ReID setting termed OneShot-OpenSet-RelD, and proposes a novel Regularised Kernel Subspace Learning model for ReID under this setting that differs significantly from existing ReID methods due to its ability of effectively learning cross-view identity-specific information from unlabelled data alone, and its flexibility of naturally accommodating pairwise labels if available.
Human Reidentification with Transferred Metric Learning
• Computer Science
ACCV
• 2012
Experiments on the VIPeR dataset and the dataset show that the proposed transferred metric learning significantly outperforms directly matching visual features or using a single generic metric learned from the whole training set.
DeepReID: Deep Filter Pairing Neural Network for Person Re-identification
• Computer Science
2014 IEEE Conference on Computer Vision and Pattern Recognition
• 2014
A novel filter pairing neural network (FPNN) to jointly handle misalignment, photometric and geometric transforms, occlusions and background clutter is proposed and significantly outperforms state-of-the-art methods on this dataset.
Person re-identification by probabilistic relative distance comparison
• Computer Science
CVPR 2011
• 2011
A novel Probabilistic Relative Distance Comparison (PRDC) model is introduced, which differs from most existing distance learning methods in that it aims to maximise the probability of a pair of true match having a smaller distance than that of a wrong match pair, which makes the model more tolerant to appearance changes and less susceptible to model over-fitting.