ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification

Résumé

Unsupervised person re-identification (ReID) aims at learning discriminative identity features without annotations. Recently, self-supervised contrastive learning has gained increasing attention for its effectiveness in unsupervised representation learning. The main idea of instance contrastive learning is to match a same instance in different augmented views. However, the relationship between different instances has not been fully explored in previous contrastive methods, especially for instance-level contrastive loss. To address this issue, we propose Interinstance Contrastive Encoding (ICE) that leverages interinstance pairwise similarity scores to boost previous classlevel contrastive ReID methods. We first use pairwise similarity ranking as one-hot hard pseudo labels for hard instance contrast, which aims at reducing intra-class variance. Then, we use similarity scores as soft pseudo labels to enhance the consistency between augmented and original views, which makes our model more robust to augmentation perturbations. Experiments on several largescale person ReID datasets validate the effectiveness of our proposed unsupervised method ICE, which is competitive with even supervised methods. Code is made available at https://github.com/chenhao2345/ICE.
Fichier principal
Vignette du fichier
iccv2021_ICE__Inter_Instance_Contrastive_Encoding_for_Unsupervised_Person_Re_identification.pdf (2.06 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03349266 , version 1 (20-09-2021)

Identifiants

  • HAL Id : hal-03349266 , version 1

Citer

Hao Chen, Benoit Lagadec, Francois F Bremond. ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification. ICCV 2021 - IEEE/CVF International Conference on Computer Vision, Oct 2021, Virtual, Canada. ⟨hal-03349266⟩
69 Consultations
38 Téléchargements

Partager

Gmail Facebook X LinkedIn More