Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigation

Xiaohan Lei1, Min Wang2, Wengang Zhou1,2, Li Li1, Houqiang Li1,2
1University of Science and Technology of China 2Institute of Artificial Intelligence, Hefei Comprehensive National Science Center
Paper Code (Coming Soon)

🎉 Accepted by CVPR 2024 ! 🎉

Abstract

As a new embodied vision task, Instance ImageGoal Navigation (IIN) aims to navigate to a specified object depicted by a goal image in an unexplored environment. The main challenge of this task lies in identifying the target object from different viewpoints while rejecting similar distractors. Existing ImageGoal Navigation methods usually adopt the simple Exploration-Exploitation framework and ignore the identification of specific instance during navigation. In this work, we propose to imitate the human behaviour of “getting closer to confirm” when distinguishing objects from a distance. Specifically, we design a new modular navigation framework named Instance-aware Exploration-Verification-Exploitation (IEVE) for instancelevel image goal navigation. Our method allows for active switching among the exploration, verification, and exploitation actions, thereby facilitating the agent in making reasonable decisions under different situations. On the challenging HabitatMatterport 3D semantic (HM3DSEM) dataset, our method surpasses previous state-of-theart work, with a classical segmentation model (0.684 vs. 0.561 success) or a robust model (0.702 vs. 0.561 success)

IEVE Switch

BibTeX

@misc{lei2024instanceaware,
      title={Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigation}, 
      author={Xiaohan Lei and Min Wang and Wengang Zhou and Li Li and Houqiang Li},
      year={2024},
      eprint={2402.17587},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}