Correctable Landmark Discovery via Large Models for Vision-Language Navigation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Bingqian, Nie, Yunshuang, Wei, Ziming, Zhu, Yi, Xu, Hang, Ma, Shikui, Liu, Jianzhuang, Liang, Xiaodan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909217040891904
author Lin, Bingqian
Nie, Yunshuang
Wei, Ziming
Zhu, Yi
Xu, Hang
Ma, Shikui
Liu, Jianzhuang
Liang, Xiaodan
author_facet Lin, Bingqian
Nie, Yunshuang
Wei, Ziming
Zhu, Yi
Xu, Hang
Ma, Shikui
Liu, Jianzhuang
Liang, Xiaodan
contents Vision-Language Navigation (VLN) requires the agent to follow language instructions to reach a target position. A key factor for successful navigation is to align the landmarks implied in the instruction with diverse visual observations. However, previous VLN agents fail to perform accurate modality alignment especially in unexplored scenes, since they learn from limited navigation data and lack sufficient open-world alignment knowledge. In this work, we propose a new VLN paradigm, called COrrectable LaNdmark DiScOvery via Large ModEls (CONSOLE). In CONSOLE, we cast VLN as an open-world sequential landmark discovery problem, by introducing a novel correctable landmark discovery scheme based on two large models ChatGPT and CLIP. Specifically, we use ChatGPT to provide rich open-world landmark cooccurrence commonsense, and conduct CLIP-driven landmark discovery based on these commonsense priors. To mitigate the noise in the priors due to the lack of visual constraints, we introduce a learnable cooccurrence scoring module, which corrects the importance of each cooccurrence according to actual observations for accurate landmark discovery. We further design an observation enhancement strategy for an elegant combination of our framework with different VLN agents, where we utilize the corrected landmark features to obtain enhanced observation features for action decision. Extensive experimental results on multiple popular VLN benchmarks (R2R, REVERIE, R4R, RxR) show the significant superiority of CONSOLE over strong baselines. Especially, our CONSOLE establishes the new state-of-the-art results on R2R and R4R in unseen scenarios. Code is available at https://github.com/expectorlin/CONSOLE.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18721
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Correctable Landmark Discovery via Large Models for Vision-Language Navigation
Lin, Bingqian
Nie, Yunshuang
Wei, Ziming
Zhu, Yi
Xu, Hang
Ma, Shikui
Liu, Jianzhuang
Liang, Xiaodan
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Vision-Language Navigation (VLN) requires the agent to follow language instructions to reach a target position. A key factor for successful navigation is to align the landmarks implied in the instruction with diverse visual observations. However, previous VLN agents fail to perform accurate modality alignment especially in unexplored scenes, since they learn from limited navigation data and lack sufficient open-world alignment knowledge. In this work, we propose a new VLN paradigm, called COrrectable LaNdmark DiScOvery via Large ModEls (CONSOLE). In CONSOLE, we cast VLN as an open-world sequential landmark discovery problem, by introducing a novel correctable landmark discovery scheme based on two large models ChatGPT and CLIP. Specifically, we use ChatGPT to provide rich open-world landmark cooccurrence commonsense, and conduct CLIP-driven landmark discovery based on these commonsense priors. To mitigate the noise in the priors due to the lack of visual constraints, we introduce a learnable cooccurrence scoring module, which corrects the importance of each cooccurrence according to actual observations for accurate landmark discovery. We further design an observation enhancement strategy for an elegant combination of our framework with different VLN agents, where we utilize the corrected landmark features to obtain enhanced observation features for action decision. Extensive experimental results on multiple popular VLN benchmarks (R2R, REVERIE, R4R, RxR) show the significant superiority of CONSOLE over strong baselines. Especially, our CONSOLE establishes the new state-of-the-art results on R2R and R4R in unseen scenarios. Code is available at https://github.com/expectorlin/CONSOLE.
title Correctable Landmark Discovery via Large Models for Vision-Language Navigation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2405.18721