Unsupervised Person Re-Identification by Deep Asymmetric Metric Embedding (English)

In: IEEE Transactions on Pattern Analysis and Machine Intelligence   ;  42 ,  4  ;  956-973  ;  2020

How to get this document?

Download
Commercial Copyright fee: €28.50 Basic fee: €4.00 Total price: €32.50
Academic Copyright fee: €28.50 Basic fee: €2.00 Total price: €30.50

Person re-identification (Re-ID) aims to match identities across non-overlapping camera views. Researchers have proposed many supervised Re-ID models which require quantities of cross-view pairwise labelled data. This limits their scalabilities to many applications where a large amount of data from multiple disjoint camera views is available but unlabelled. Although some unsupervised Re-ID models have been proposed to address the scalability problem, they often suffer from the view-specific bias problem which is caused by dramatic variances across different camera views, e.g., different illumination, viewpoints and occlusion. The dramatic variances induce specific feature distortions in different camera views, which can be very disturbing in finding cross-view discriminative information for Re-ID in the unsupervised scenarios, since no label information is available to help alleviate the bias. We propose to explicitly address this problem by learning an unsupervised asymmetric distance metric based on cross-view clustering. The asymmetric distance metric allows specific feature transformations for each camera view to tackle the specific feature distortions. We then design a novel unsupervised loss function to embed the asymmetric metric into a deep neural network, and therefore develop a novel unsupervised deep framework named the DEep Clustering-based Asymmetric MEtric Learning (DECAMEL). In such a way, DECAMEL jointly learns the feature representation and the unsupervised asymmetric metric. DECAMEL learns a compact cross-view cluster structure of Re-ID data, and thus help alleviate the view-specific bias and facilitate mining the potential cross-view discriminative information for unsupervised Re-ID. Extensive experiments on seven benchmark datasets whose sizes span several orders show the effectiveness of our framework.

  • Title:
    Unsupervised Person Re-Identification by Deep Asymmetric Metric Embedding
  • Author / Creator:
  • Published in:
  • Publisher:
    IEEE
  • Year of publication:
    2020
  • Size:
    2745600 byte
  • ISSN:
  • DOI:
  • Type of media:
    Article (Journal)
  • Type of material:
    Electronic Resource
  • Language:
    English
  • Source:
  • Export:
  • ORKG:

Table of contents – Volume 42, Issue 4

Show all volumes and issues

The tables of contents are generated automatically and are based on the data records of the individual contributions available in the index of the TIB portal. The display of the Tables of Contents may therefore be incomplete.

765
A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation
Kuehne, Hilde / Richard, Alexander / Gall, Juergen | 2020
780
Automated Video Face Labelling for Films and TV Material
Parkhi, Omkar M. / Rahtu, Esa / Cao, Qiong / Zisserman, Andrew | 2020
793
Baselines Extraction from Curved Document Images via Slope Fields Recovery
Meng, Gaofeng / Pan, Chunhong / Xiang, Shiming / Wu, Ying | 2020
809
Deep Self-Evolution Clustering
Chang, Jianlong / Meng, Gaofeng / Wang, Lingfeng / Xiang, Shiming / Pan, Chunhong | 2020
824
Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs
Malkov, Yu A. / Yashunin, D. A. | 2020
837
Extracting Geometric Structures in Images with Delaunay Point Processes
Favreau, Jean-Dominique / Lafarge, Florent / Bousseau, Adrien / Auvolat, Alex | 2020
851
Group Maximum Differentiation Competition: Model Comparison with Few Samples
Ma, Kede / Duanmu, Zhengfang / Wang, Zhou / Wu, Qingbo / Liu, Wentao / Yong, Hongwei / Li, Hongliang / Zhang, Lei | 2020
865
Hierarchical Bayesian Inverse Lighting of Portraits with a Virtual Light Stage
Shahlaei, Davoud / Blanz, Volker | 2020
880
Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis Using Structural MRI
Lian, Chunfeng / Liu, Mingxia / Zhang, Jun / Shen, Dinggang | 2020
894
On Detection of Faint Edges in Noisy Images
Ofir, Nati / Galun, Meirav / Alpert, Sharon / Brandt, Achi / Nadler, Boaz / Basri, Ronen | 2020
909
Perspective-Adaptive Convolutions for Scene Parsing
Zhang, Rui / Tang, Sheng / Zhang, Yongdong / Li, Jintao / Yan, Shuicheng | 2020
925
Tensor Robust Principal Component Analysis with a New Tensor Nuclear Norm
Lu, Canyi / Feng, Jiashi / Chen, Yudong / Liu, Wei / Lin, Zhouchen / Yan, Shuicheng | 2020
939
Tracking-by-Fusion via Gaussian Process Regression Extended to Transfer Learning
Gao, Jin / Wang, Qiang / Xing, Junliang / Ling, Haibin / Hu, Weiming / Maybank, Stephen | 2020
956
Unsupervised Person Re-Identification by Deep Asymmetric Metric Embedding
Yu, Hong-Xing / Wu, Ancong / Zheng, Wei-Shi | 2020
974
Visibility Graphs for Image Processing
Iacovacci, Jacopo / Lacasa, Lucas | 2020
988
Weighted Manifold Alignment using Wave Kernel Signatures for Aligning Medical Image Datasets
Clough, James R. / Balfour, Daniel R. / Cruz, Gastao / Marsden, Paul K. / Prieto, Claudia / Reader, Andrew J. / King, Andrew P. | 2020
998
Denoising Autoencoders for Overgeneralization in Neural Networks
Spigler, Giacomo | 2020
1005
Efficient Graph Cut Optimization for Full CRFs with Quantized Edges
Veksler, Olga | 2020
1013
Learning Raw Image Reconstruction-Aware Deep Image Compressors
Punnappurath, Abhijith / Brown, Michael S. | 2020
1020
2020 COMPSAC CFP
| 2020
C1
Table of Contents
| 2020
C2
Cover
| 2020