Источник
CVPR
Дата публикации
05.06.2023
Авторы
Александр Панов Дмитрий Юдин Маргарита Кичик Татьяна Земскова
Поделиться

SegmATRon: Embodied Adaptive Semantic Segmentation for Indoor Environment

Аннотация

This paper presents an adaptive transformer model named SegmATRon for embodied image semantic segmentation. Its distinctive feature is the adaptation of model weights during inference on several images using a hybrid multicomponent loss function. We studied this model on datasets collected in the photorealistic Habitat Simulator. We showed that obtaining additional images using the agent's actions in an indoor environment can improve the quality of semantic segmentation.

Присоединяйтесь к AIRI в соцсетях