• Home
  • Search
  • Efficient Online Local Metric Adaptation via Negative Samples for Person Re-identification
  • Cite Icon97
  • https://doi.org/10.1109/iccv.2017.265Copy DOI Icon

Efficient Online Local Metric Adaptation via Negative Samples for Person Re-identification

  • Oct 1, 2017
  • Jiahuan Zhou +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Many existing person re-identification (PRID) methods typically attempt to train a faithful global metric offline to cover the enormous visual appearance variations, so as to directly use it online on various probes for identity matching. However, their need for a huge set of positive training pairs is very demanding in practice. In contrast to these methods, this paper advocates a different paradigm: part of the learning can be performed online but with nominal costs, so as to achieve online metric adaptation for different input probes. A major challenge here is that no positive training pairs are available for the probe anymore. By only exploiting easily-available negative samples, we propose a novel solution to achieve local metric adaptation effectively and efficiently. For each probe at the test time, it learns a strictly positive semi-definite dedicated local metric. Comparing to offline global metric learning, its computational cost is negligible. The insight of this new method is that the local hard negative samples can actually provide tight constraints to fine tune the metric locally. This new local metric adaptation method is generally applicable, as it can be used on top of any global metric to enhance its performance. In addition, this paper gives in-depth theoretical analysis and justification of the new method. We prove that our new method guarantees the reduction of the classification error asymptotically, and prove that it actually learns the optimal local metric to best approximate the asymptotic case by a finite number of training data. Extensive experiments and comparative studies on almost all major benchmarks (VIPeR, QMUL GRID, CUHK Campus, CUHK03 and Market-1501) have confirmed the effectiveness and superiority of our method.

Similar Papers
  • Research Article
  • Citations7

Learning Visual Instance Retrieval from Failure: Efficient Online Local Metric Adaptation from Negative Samples.

  • Jan 01, 2019
  • IEEE transactions on pattern analysis and machine intelligence
  • Jiahuan Zhou +1
  • Conference Article
  • Citations3

Triplet CNN and pedestrian attribute recognition for improved person re-identification

  • Aug 01, 2017
  • Yiqiang Chen +4
  • PDF
  • Research Article
  • Citations13

Person Re-Identification With Joint Verification and Identification of Identity-Attribute Labels

  • Jan 01, 2019
  • IEEE Access
  • Shun Zhang +5
  • Book Chapter
  • Citations2

Adaptive Margin Nearest Neighbor for Person Re-Identification

  • Jan 01, 2015
  • Lei Yao +6
  • Research Article
  • Citations1

Unsupervised Person Re-Identification via Deep Attribute Learning

  • Aug 15, 2025
  • Future Internet
  • Shun Zhang +4
  • Conference Article
  • Citations4

Exploiting low-rank structures from cross-camera images for robust person re-identification

  • Oct 01, 2014
  • Ming-Hang Fu +2
  • Research Article
  • Citations73

Multi-type attributes driven multi-camera person re-identification

  • Sep 12, 2017
  • Pattern Recognition
  • Chi Su +4
  • Conference Article
  • Citations4

Person re-identification via region-of-interest based features

  • Dec 01, 2014
  • Jianlou Si +2
  • Research Article
  • Citations31

Multiple metric learning based on bar-shape descriptor for person re-identification

  • Jun 08, 2017
  • Pattern Recognition
  • Cairong Zhao +5
  • Research Article
  • Citations237

Person Re-Identification by Discriminative Selection in Video Ranking.

  • Jan 27, 2016
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Taiqing Wang +3
  • Conference Article
  • Citations37

Repeated Pattern Detection Using CNN Activations

  • Mar 01, 2017
  • Louis Lettry +3
  • Research Article
  • Citations50

Uniform and Variational Deep Learning for RGB-D Object Recognition and Person Re-Identification.

  • May 15, 2019
  • IEEE Transactions on Image Processing
  • Liangliang Ren +3
  • Conference Article
  • Citations41

Alextrac: Affinity learning by exploring temporal reinforcement within association chains

  • May 01, 2016
  • Alex Bewley +3
  • Book Chapter
  • Citations698

Person Re-identification by Video Ranking

  • Jan 01, 2014
  • Taiqing Wang +3
  • Research Article
  • Citations16

Fusion of Multiple Person Re-id Methods With Model and Data-Aware Abilities.

  • Oct 09, 2018
  • IEEE Transactions on Cybernetics
  • De Cheng +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.