ESceme: Vision-and-Language Navigation with Episodic Scene Memory
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909254567329792 |
|---|---|
| author | Zheng, Qi Liu, Daqing Wang, Chaoyue Zhang, Jing Wang, Dadong Tao, Dacheng |
| author_facet | Zheng, Qi Liu, Daqing Wang, Chaoyue Zhang, Jing Wang, Dadong Tao, Dacheng |
| contents | Vision-and-language navigation (VLN) simulates a visual agent that follows natural-language navigation instructions in real-world scenes. Existing approaches have made enormous progress in navigation in new environments, such as beam search, pre-exploration, and dynamic or hierarchical history encoding. To balance generalization and efficiency, we resort to memorizing visited scenarios apart from the ongoing route while navigating. In this work, we introduce a mechanism of Episodic Scene memory (ESceme) for VLN that wakes an agent's memories of past visits when it enters the current scene. The episodic scene memory allows the agent to envision a bigger picture of the next prediction. This way, the agent learns to utilize dynamically updated information instead of merely adapting to the current observations. We provide a simple yet effective implementation of ESceme by enhancing the accessible views at each location and progressively completing the memory while navigating. We verify the superiority of ESceme on short-horizon (R2R), long-horizon (R4R), and vision-and-dialog (CVDN) VLN tasks. Our ESceme also wins first place on the CVDN leaderboard. Code is available: \url{https://github.com/qizhust/esceme}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_01032 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | ESceme: Vision-and-Language Navigation with Episodic Scene Memory Zheng, Qi Liu, Daqing Wang, Chaoyue Zhang, Jing Wang, Dadong Tao, Dacheng Computer Vision and Pattern Recognition Vision-and-language navigation (VLN) simulates a visual agent that follows natural-language navigation instructions in real-world scenes. Existing approaches have made enormous progress in navigation in new environments, such as beam search, pre-exploration, and dynamic or hierarchical history encoding. To balance generalization and efficiency, we resort to memorizing visited scenarios apart from the ongoing route while navigating. In this work, we introduce a mechanism of Episodic Scene memory (ESceme) for VLN that wakes an agent's memories of past visits when it enters the current scene. The episodic scene memory allows the agent to envision a bigger picture of the next prediction. This way, the agent learns to utilize dynamically updated information instead of merely adapting to the current observations. We provide a simple yet effective implementation of ESceme by enhancing the accessible views at each location and progressively completing the memory while navigating. We verify the superiority of ESceme on short-horizon (R2R), long-horizon (R4R), and vision-and-dialog (CVDN) VLN tasks. Our ESceme also wins first place on the CVDN leaderboard. Code is available: \url{https://github.com/qizhust/esceme}. |
| title | ESceme: Vision-and-Language Navigation with Episodic Scene Memory |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2303.01032 |