Predictive Uncertainty Estimation for Camouflaged Object Detection - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Image Processing Année : 2023

Predictive Uncertainty Estimation for Camouflaged Object Detection

Résumé

Uncertainty is inherent in machine learning methods, especially those for camouflaged object detection aiming to finely segment the objects concealed in background. The strong enquote center bias of the training dataset leads to models of poor generalization ability as the models learn to find camouflaged objects around image center, which we define as enquote model bias. Further, due to the similar appearance of camouflaged object and its surroundings, it is difficult to label the accurate scope of the camouflaged object, especially along object boundaries, which we term as enquote data bias. To effectively model the two types of biases, we resort to uncertainty estimation and introduce predictive uncertainty estimation technique, which is the sum of model uncertainty and data uncertainty, to estimate the two types of biases simultaneously. Specifically, we present a predictive uncertainty estimation network ( PUENet ) that consists of a Bayesian conditional variational auto-encoder (BCVAE) to achieve predictive uncertainty estimation, and a predictive uncertainty approximation (PUA) module to avoid the expensive sampling process at test-time. Experimental results show that our PUENet achieves both highly accurate prediction, and reliable uncertainty estimation representing the biases within both model parameters and the datasets.
Fichier principal
Vignette du fichier
Zhang et al. - 2023 - Predictive Uncertainty Estimation for Camouflaged .pdf (10.98 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04142929 , version 1 (13-07-2023)

Licence

Paternité - Pas d'utilisation commerciale

Identifiants

Citer

Yi Zhang, Jing Zhang, Wassim Hamidouche, Olivier Deforges. Predictive Uncertainty Estimation for Camouflaged Object Detection. IEEE Transactions on Image Processing, 2023, 32, pp.3580-3591. ⟨10.1109/TIP.2023.3287137⟩. ⟨hal-04142929⟩
181 Consultations
53 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More