Research map / Vision-language and multimodal / Robot action and navigation
Vision-Language Navigation With Random Environmental Mixup
Chong Liu, Fengda Zhu, Xiaojun Chang, Xiaodan Liang, Zongyuan Ge, Yi-Dong Shen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add REM augmentation | VLN-Bert · R2R test unseen | SR (%): 61.4 -> 65.2 | Improved |
| add REM augmentation | VLN-Bert · R2R val unseen | SR (%): 61.4 -> 63.6 | Improved |
| add REM augmentation | EnvDrop · R2R val unseen | SR (%): 51.1 -> 53.8 | Improved |
| add REM augmentation | IL+RL · R2R val unseen | SR (%): 46.2 -> 48.6 | Improved |
| add REM augmentation | VLN-Bert · R4R val unseen | SR (%): 42.5 -> 46.0 | Improved |
| add REM augmentation | EnvDrop · R4R val unseen | SPL (%): 21.0 -> 25.0 | Improved |
| add REM augmentation | IL+RL · R2R val seen | SR (%): 53.8 -> 58.2 | Improved |
| add orientation alignment (without CCV) (ablation) | REM on IL+RL · R2R val unseen | SR (%): 46.0 -> 47.2 | Improved |
| add orientation alignment (with CCV) (ablation) | REM on IL+RL · R2R val unseen | SR (%): 46.9 -> 48.6 | Improved |
| add cross-viewpoint visual replacement after alignment (ablation) | REM on IL+RL · R2R val unseen | SR (%): 47.2 -> 48.6 | Improved |
| add REM without orientation alignment (ablation) | IL+RL · R2R val unseen | SR (%): 46.2 -> 46.0 | Hurt |
| replace 3 views instead of 0 (ablation) | REM on IL+RL · R2R val unseen | SR (%): 47.2 -> 48.6 | Improved |
Closest papers by meaning
- Bridging the Visual Semantic Gap in VLN via Semantically Richer Instructions (ECCV 2022 · similarity 0.88)
- Frequency-Enhanced Data Augmentation for Vision-and-Language Navigation (NeurIPS 2023 · similarity 0.88)
- Vision-Language Navigation Policy Learning and Adaptation (TPAMI 2020 · similarity 0.88)
- EnvEdit: Environment Editing for Vision-and-Language Navigation (CVPR 2022 · similarity 0.88)
- Volumetric Environment Representation for Vision-Language Navigation (CVPR 2024 · similarity 0.87)
- General Scene Adaptation for Vision-and-Language Navigation (ICLR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
