paper-with-me

홈 › Papers

CLEAR: Improving Vision-Language Navigation with Cross-Lingual, Environment-Agnostic Representations

2022-07-05 · Findings (NAACL) 2022 7 · Jialu Li, Hao Tan, Mohit Bansal

Vision-and-Language Navigation (VLN) tasks require an agent to navigate through the environment based on language instructions. In this paper, we aim to solve two key challenges in this task: utilizing multilingual instructions for improved instruction-path grounding and navigating through new environments that are unseen during training. To address these challenges, we propose CLEAR: Cross-Lingual and Environment-Agnostic Representations. First, our agent learns a shared and visually-aligned cross-lingual language representation for the three languages (English, Hindi and Telugu) in the Room-Across-Room dataset. Our language representation learning is guided by text pairs that are aligned by visual information. Second, our agent learns an environment-agnostic visual representation by maximizing the similarity between semantically-aligned image pairs (with constraints on object-matching) from different environments. Our environment agnostic visual representation can mitigate the environment bias induced by low-level visual information. Empirically, on the Room-Across-Room dataset, we show that our multilingual agent gets large improvements in all metrics over the strong baseline model when generalizing to unseen environments with the cross-lingual language representation and the environment-agnostic visual representation. Furthermore, we show that our learned language and visual representations can be successfully transferred to the Room-to-Room and Cooperative Vision-and-Dialogue Navigation task, and present detailed qualitative and quantitative generalization and grounding analysis. Our code is available at https://github.com/jialuli-luka/CLEAR

📄 PDF Abstract BibTeX arXiv:2207.02185

Code (1)

jialuli-luka/clear 공식 구현 pytorch

Tasks

NavigateRepresentation LearningVision and Language NavigationVision-Language Navigation

Similar Papers 제목 키워드 기반

Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding

2020-10-15 · EMNLP 2020 11 · Alexander Ku, Peter Anderson, Roma Patel, Eugene Ie 외

We introduce Room-Across-Room (RxR), a new Vision-and-Language Navigation (VLN) dataset. RxR is multilingual (English, Hindi, and Telugu) and larger (more paths and instructions) than other VLN datasets. It emphasizes th…

Vision and Language Navigation

Accessible Instruction-Following Agent

2023-05-08 · Kairui Zhou

Humans can collaborate and complete tasks based on visual signals and instruction from the environment. Training such a robot is difficult especially due to the understanding of the instruction and the complicated enviro…

Instruction FollowingLanguage ModelingLanguage ModellingLarge Language Model+3

Cross-Lingual Vision-Language Navigation

2019-10-24 · An Yan, Xin Eric Wang, Jiangtao Feng, Lei LI 외

Commanding a robot to navigate with natural language instructions is a long-term goal for grounded language understanding and robotics. But the dominant language is English, according to previous studies on vision-langua…

Domain AdaptationNavigateVision-Language NavigationZero-Shot Learning

Diagnosing Vision-and-Language Navigation: What Really Matters

2021-03-30 · NAACL 2022 7 · Wanrong Zhu, Yuankai Qi, Pradyumna Narayana, Kazoo Sone 외

Vision-and-language navigation (VLN) is a multimodal task where an agent follows natural language instructions and navigates in visual environments. Multiple setups have been proposed, and researchers apply new model arc…

DiagnosticObjectVision and Language Navigation

Diagnosing Vision-and-Language Navigation: What Really Matters

2021-12-17 · ACL ARR December 2022 12 · Anonymous

Vision-and-language navigation (VLN) is a multimodal task where an agent follows natural language instructions and navigates in visual environments. Multiple setups have been proposed, and researchers apply new model arc…

DiagnosticObjectVision and Language Navigation