Oct 14, 2022 · In this paper, we propose a multi-granularity map, which contains both object fine-grained details (eg, color, texture) and semantic classes, to represent ...

We address a practical yet challenging problem of training robot agents to navigate in an environment following a path described by some language ...

Oct 31, 2022 · This paper presents a map-based method for Vision-and-Language Navigation (VLN). The approach builds a semantic map which includes object ...

Official Pytorch implementation for NeurIPS 2022 paper "Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation”

We follow VLN-CE [5] to evaluate the navigation process in terms of success rate (SR), oracle success rate (OS), success weighted by path length (SPL), ...

Oct 14, 2022 · We address a practical yet challenging problem of training robot agents to navigate in an environment following a path described by some ...

We address a practical yet challenging problem of training robot agents to navigate in an environment following a path described by some language ...

Explore all code implementations available for Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation.

WS-MGMap Public. Official Pytorch implementation for NeurIPS 2022 paper "Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation”.

For example, WS-MGMap [8] proposes a multi-granularity map and introduces a weakly-supervised auxiliary task to learn a better map representation that reveals ...