CANU-ReID: A Conditional Adversarial Network for Unsupervised person Re-IDentification - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

CANU-ReID: A Conditional Adversarial Network for Unsupervised person Re-IDentification

(1) , (1) , (2, 3, 4) , (1) , (1)
1
2
3
4

Abstract

Unsupervised person re-ID is the task of identifying people on a target data set for which the ID labels are unavailable during training. In this paper, we propose to unify two trends in unsupervised person re-ID: clustering & fine-tuning and adversarial learning. On one side, clustering groups training images into pseudo-ID labels, and uses them to fine-tune the feature extractor. On the other side, adversarial learning is used, inspired by domain adaptation, to match distributions from different domains. Since target data is distributed across different camera viewpoints, we propose to model each camera as an independent domain, and aim to learn domain-independent features. Straightforward adversarial learning yields negative transfer, we thus introduce a conditioning vector to mitigate this undesirable effect. In our framework, the centroid of the cluster to which the visual sample belongs is used as conditioning vector of our conditional adversarial network, where the vector is permutation invariant (clusters ordering does not matter) and its size is independent of the number of clusters. To our knowledge, we are the first to propose the use of conditional adversar-ial networks for unsupervised person re-ID. We evaluate the proposed architecture on top of two state-of-the-art clustering-based unsupervised person re-identification (re-ID) methods on four different experimental settings with three different data sets and set the new state-of-the-art performance on all four of them. Our code and model will be made publicly available at https://team.inria.fr/perception/canu-reid/.
Fichier principal
Vignette du fichier
delorme_icpr2020.pdf (772.83 Ko) Télécharger le fichier
Vignette du fichier
CANU_oral.pdf (3.48 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02882285 , version 1 (26-06-2020)

Identifiers

Cite

Guillaume Delorme, Yihong Xu, Stéphane Lathuilière, Radu Horaud, Xavier Alameda-Pineda. CANU-ReID: A Conditional Adversarial Network for Unsupervised person Re-IDentification. ICPR 2020 - 25th International Conference on Pattern Recognition, Jan 2021, Milano, Italy. pp.4428-4435, ⟨10.1109/ICPR48806.2021.9412431⟩. ⟨hal-02882285⟩
508 View
571 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More