HyperAI
AccueilActualitésArticles de recherche récentsTutorielsEnsembles de donnéesWikiSOTAModèles LLMClassement GPUÉvénements
Recherche
À propos
HyperAI

Overlapped 50 50 On Ade20K

Métriques

mIoU

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle
mIoU
Paper TitleRepository
MiB29.31PLOP: Learning without Forgetting for Continual Semantic Segmentation
PLOP30.4PLOP: Learning without Forgetting for Continual Semantic Segmentation
RCNet-10132.5Representation Compensation Networks for Continual Semantic Segmentation
SSUL-M29.77SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning
MiB+AWT33.5Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation
MBS45.4Mitigating Background Shift in Class-Incremental Semantic Segmentation
SSUL29.56SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning
0 of 7 row(s) selected.