Vision-language Navigation With Random Environmental Mixup | Awesome LLM Papers Add your paper to Awesome LLM Papers

Vision-language Navigation With Random Environmental Mixup

Chong Liu, Fengda Zhu, Xiaojun Chang, Xiaodan Liang, Zongyuan Ge, Yi-Dong Shen . 2021 IEEE/CVF International Conference on Computer Vision (ICCV) 2021 – 55 citations

[Code] [Paper]   Search on Google Scholar   Search on Semantic Scholar
3d Representation Agentic Datasets Ethics & Fairness Evaluation Has Code ICCV Image Text Integration Multimodal Semantic Representation Visual Contextualization

Vision-language Navigation (VLN) tasks require an agent to navigate step-by-step while perceiving the visual observations and comprehending a natural language instruction. Large data bias, which is caused by the disparity ratio between the small data scale and large navigation space, makes the VLN task challenging. Previous works have proposed various data augmentation methods to reduce data bias. However, these works do not explicitly reduce the data bias across different house scenes. Therefore, the agent would overfit to the seen scenes and achieve poor navigation performance in the unseen scenes. To tackle this problem, we propose the Random Environmental Mixup (REM) method, which generates cross-connected house scenes as augmented data via mixuping environment. Specifically, we first select key viewpoints according to the room connection graph for each scene. Then, we cross-connect the key views of different scenes to construct augmented scenes. Finally, we generate augmented instruction-path pairs in the cross-connected scenes. The experimental results on benchmark datasets demonstrate that our augmentation data via REM help the agent reduce its performance gap between the seen and unseen environment and improve the overall performance, making our model the best existing approach on the standard VLN benchmark. The code have released: https://github.com/LCFractal/VLNREM.

Similar Work