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 and the synthetic AI2-THOR Simulators. We showed that obtaining additional images using the agent's actions in an indoor environment can improve the quality of semantic segmentation. The code of the proposed approach and datasets are publicly available at https://github.com/wingrune/SegmATRon.
@article{arxiv.2310.12031,
title = {SegmATRon: Embodied Adaptive Semantic Segmentation for Indoor Environment},
author = {Tatiana Zemskova and Margarita Kichik and Dmitry Yudin and Aleksei Staroverov and Aleksandr Panov},
journal= {arXiv preprint arXiv:2310.12031},
year = {2023}
}