ru
ru
Source
CVPR
DATE OF PUBLICATION
06/05/2023
Authors
Alexander Panov Dmitry Yudin Margarita Kichik Tatiana Zemskova
Share

SegmATRon: Embodied Adaptive Semantic Segmentation for Indoor Environment

Embodied semantic segmentation, Image recognition, Indoor environment, Transformer, Adaptive model

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 Simulator. We showed that obtaining additional images using the agent's actions in an indoor environment can improve the quality of semantic segmentation.

Full text

Similar publications

IROS
Model-based Policy Optimization using Symbolic World Model
Andrey Gorodetsky, Konstantin Mironov, Alexander Panov
SOURCE
ECAI
Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual Environments
Zoya Volovikova, Alexey Skrynnik, Peter Kuderov, Alexander Panov
SOURCE
Artificial Intelligence
Generative models for grid-based and image-based pathfinding
Daniil Kirilenko, Anton Andreychuk, Alexander Panov, Konstantin Yakovlev
SOURCE
Pattern Recognition and Image Analysis
Skill Learning with Empowerment in Reinforcement Learning
Artem Latyshev, Alexander Panov
SOURCE
Cognitive Systems Research
Hebbian spatial encoder with adaptive sparse connectivity
Peter Kuderov, Evgenii Dzhivelikian, Alexander Panov
SOURCE
Computer Optics
Localization of mobile robot in prior 3D LiDAR maps using stereo image sequence
Ilya Belkin, Alexander Abramenko, Vitaly Bezuglyj, Dmitry Yudin
SOURCE
Neurocomputing
OFMPNet: Deep end-to-end model for occupancy and flow prediction in urban environment
Youshaa Murhij, Dmitry Yudin
SOURCE
Contact us
Join AIRI
You can ask us a question or suggest a joint project in the field of AI

Message sent.

Thank you!

Something went wrong. Try again