vix.ing · top · new · best · stats · spec

SegmATRon: Embodied Adaptive Semantic Segmentation for Indoor Environment

2023/10/18 by Tatiana Zemskova, Zemskova, Tatiana, Margarita Kichik +7
Computer Science · #Advanced Image and Video Retrieval Techniques #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications

paper · pdf · doi:10.48550/arxiv.2310.12031

openalex publication_date 2023/10/18 · openalex created_date 2023/10/21 · openalex updated_date 2026/07/28

Abstract

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.

Related