Skip to Main content Skip to Navigation
Conference papers

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

Guillaume Delorme 1 Yihong Xu 1 Stéphane Lathuilière 1, 2 Radu Horaud 1 Xavier Alameda-Pineda 1
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : Fig. 1: Clustering-based (left) vs. conditional adversarial clustering-based (right) unsupervised person re-ID. Our intuition is that features should be camera-independent, and thus the clustering result should group visual features by ID rather than by camera. Our method conditions a camera-based adversarial discriminator with the visual features corresponding to the cluster's centroid. 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/.
Complete list of metadatas

Cited literature [43 references]  Display  Hide  Download

https://hal.inria.fr/hal-02882285
Contributor : Team Perception <>
Submitted on : Friday, June 26, 2020 - 3:41:22 PM
Last modification on : Friday, July 3, 2020 - 4:49:11 PM

File

delorme_icpr2020.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02882285, version 1

Citation

Guillaume Delorme, Yihong Xu, Stéphane Lathuilière, Radu Horaud, Xavier Alameda-Pineda. CANU-ReID: A Conditional Adversarial Network for Unsupervised person Re-IDentification. International Conference on Pattern Recognition, Jan 2021, Milano, Italy. ⟨hal-02882285⟩

Share

Metrics

Record views

155

Files downloads

114