Online Depth Learning Against Forgetting in Monocular Videos - Département Image, Données, Signal Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Online Depth Learning Against Forgetting in Monocular Videos

Zhenyu Zhang
  • Fonction : Auteur
Elisa Ricci
  • Fonction : Auteur
Nicu Sebe
  • Fonction : Auteur
  • PersonId : 1077416
Yan Yan
  • Fonction : Auteur
Jian Yang

Résumé

Online depth learning is the problem of consistently adapting a depth estimation model to handle a continuously changing environment. This problem is challenging due to the network easily overfits on the current environment and forgets its past experiences. To address such problem , this paper presents a novel Learning to Prevent Forgetting (LPF) method for online mono-depth adaptation to new target domains in unsupervised manner. Instead of updating the universal parameters, LPF learns adapter modules to efficiently adjust the feature representation and distribution without losing the pre-learned knowledge in online condition. Specifically, to adapt temporal-continuous depth patterns in videos, we introduce a novel meta-learning approach to learn adapter modules by combining online adaptation process into the learning objective. To further avoid overfitting, we propose a novel temporal-consistent regu-larization to harmonize the gradient descent procedure at each online learning step. Extensive evaluations on real-world datasets demonstrate that the proposed method, with very limited parameters, significantly improves the estimation quality.
Fichier principal
Vignette du fichier
Zhang_Online_Depth_Learning_Against_Forgetting_in_Monocular_Videos_CVPR_2020_paper.pdf (1.37 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-02941952 , version 1 (17-09-2020)

Identifiants

  • HAL Id : hal-02941952 , version 1

Citer

Zhenyu Zhang, Stéphane Lathuilière, Elisa Ricci, Nicu Sebe, Yan Yan, et al.. Online Depth Learning Against Forgetting in Monocular Videos. IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2020, Seattle, United States. ⟨hal-02941952⟩
100 Consultations
162 Téléchargements

Partager

Gmail Facebook X LinkedIn More