Research map / Vision-language and multimodal / Robot action and navigation
Transferable Representation Learning in Vision-and-Language Navigation
Haoshuo Huang, Vihan Jain, Harsh Mehta, Alexander Ku, Gabriel Magalhaes, Jason Baldridge, Eugene Ie
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 CMA+NVS pretrained encoders (ablation) | RCM agent · R2R Val Unseen | SPL: 32.7 -> 43.0 | Improved |
| add CMA+NVS pretrained encoders (ablation) | RCM agent · R2R Val Unseen | SR: 41.1 -> 46.1 | Improved |
| add CMA+NVS pretrained encoders (ablation) | Speaker-Follower agent · R2R Val Unseen | SPL: 29.0 -> 31.2 | Improved |
| add CMA+NVS pretrained encoders (ablation) | Speaker-Follower agent · R2R Val Unseen | SR: 36.0 -> 40.0 | Improved |
| add CMA-only pretraining (ablation) | RCM agent · R2R Val Unseen | SPL: 32.7 -> 42.0 | Improved |
| add CMA-only pretraining (ablation) | Speaker-Follower agent · R2R Val Unseen | SPL: 29.0 -> 26.8 | Hurt |
| add NVS-only pretraining (ablation) | RCM agent · R2R Val Unseen | SPL: 32.7 -> 20.6 | Hurt |
| add NVS-only pretraining (ablation) | Speaker-Follower agent · R2R Val Unseen | SR: 36.0 -> 34.9 | Hurt |
| add NVS loss to CMA training (ablation) | auxiliary alignment model · CMA validation (PR+RW), Val Unseen | AUC: 72.0 -> 79.2 | Improved |
| add NVS loss to CMA training (ablation) | auxiliary alignment model · CMA validation (PR+RW), Val Seen | AUC: 82.6 -> 84.0 | Improved |
| warm-start both image and language encoders vs only image encoder (ablation) | RCM agent · R2R Val Unseen | SPL: 33.1 -> 43.0 | Improved |
| warm-start both image and language encoders vs only language encoder (ablation) | RCM agent · R2R Val Unseen | SPL: 35.8 -> 43.0 | Improved |
Closest papers by meaning
- Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-Training (CVPR 2020 · similarity 0.91)
- A New Path: Scaling Vision-and-Language Navigation With Synthetic Instructions and Imitation Learning (CVPR 2023 · similarity 0.90)
- Vision-Based Navigation With Language-Based Assistance via Imitation Learning With Indirect Intervention (CVPR 2019 · similarity 0.90)
- Curriculum Learning for Vision-and-Language Navigation (NeurIPS 2021 · similarity 0.90)
- Vision-Language Navigation Policy Learning and Adaptation (TPAMI 2020 · similarity 0.90)
- General Scene Adaptation for Vision-and-Language Navigation (ICLR 2025 · similarity 0.89)
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.
