Which way is `right'?: Uncovering limitations of Vision-and-Language Navigation model
원문 초록
The challenging task of Vision-and-Language Navigation (VLN) requires embodied agents to follow natural language instructions to reach a goal location or object (e.g. `walk down the hallway and turn left at the piano'). For agents to complete this task successfully, they must be able to ground objects referenced into the instruction (e.g.`piano') into the visual scene as well as ground directional phrases (e.g.`turn left') into actions. In this work we ask the following question -- to what degree are spatial and directional language cues informing the navigation model's decisions? We propose a series of simple masking experiments to inspect the model's reliance on different parts of the instruction. Surprisingly we uncover that certain top performing models rely only on the noun tokens of the instructions. We propose two training methods to alleviate this concerning limitation.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments
A Navigation Framework Utilizing Vision-Language Models
Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigation
FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models
Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation
CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory
토론
이 논문과 연결된 포럼 글이 아직 없습니다.