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}
}
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… 

Figures and Tables from this paper

Unsupervised Person Re-Identification by Deep Asymmetric Metric Embedding
TLDR
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
TLDR
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
TLDR
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
TLDR
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
TLDR
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
TLDR
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
TLDR
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
TLDR
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
TLDR
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
TLDR
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
TLDR
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
TLDR
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
TLDR
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
  • Shengcai Liao, S. Li
  • Computer Science
    2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
TLDR
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
TLDR
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
TLDR
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
TLDR
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
TLDR
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
TLDR
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.
...
...