視覚と言語によるナビゲーションのためのクロスモーダル地図学習
Cross-modal Map Learning for Vision and Language Navigation
言語と視覚の対応を明示的な空間表現（地図）上で学習し、観測・未観測領域の上面視意味地図を予測して経路をウェイポイントとして出力するVLN手法を提案した論文。
著者: Georgios Georgakis, Karl Schmeckpeper, Karan Wanchoo, Soham Dan, Eleni Miltsakaki, Dan Roth, Kostas Daniilidis
分類: cs.CV, cs.RO
原文アブストラクト
We consider the problem of Vision-and-Language Navigation (VLN). The majority of current methods for VLN are trained end-to-end using either unstructured memory such as LSTM, or using cross-modal attention over the egocentric observations of the agent. In contrast to other works, our key insight is that the association between language and vision is stronger when it occurs in explicit spatial representations. In this work, we propose a cross-modal map learning model for vision-and-language navigation that first learns to predict the top-down semantics on an egocentric map for both observed and unobserved regions, and then predicts a path towards the goal as a set of waypoints. In both cases, the prediction is informed by the language through cross-modal attention mechanisms. We experimentally test the basic hypothesis that language-driven navigation can be solved given a map, and then show competitive results on the full VLN-CE benchmark.
