Research map / Vision-language and multimodal / Robot action and navigation
Airbert: In-Domain Pretraining for Vision-and-Language Navigation
Pierre-Louis Guhur, Makarand Tapaswi, Shizhe Chen, Ivan Laptev, Cordelia Schmid
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 shuffling loss during BnB pretraining (ablation) | Airbert pretraining · R2R val unseen | SR: 64.21 -> 66.52 | Improved |
| add shuffling loss during R2R fine-tuning (ablation) | Airbert · R2R val unseen | SR: 66.52 -> 66.90 | Improved |
| add shuffling loss when pretraining with BnB and Speaker data (ablation) | Airbert · R2R val unseen | SR: 65.52 -> 68.67 | Improved |
| insert captionless images at random locations in BnB paths (ablation) | Airbert pretraining · R2R val unseen | SR: 62.45 -> 66.05 | Improved |
| add instruction rephrasing, image merging and captionless insertion over concatenation (ablation) | Airbert pretraining · R2R val unseen | SR: 62.71 -> 66.52 | Improved |
| use naive concatenation instead of raw image-caption pairs (ablation) | Airbert pretraining · R2R val unseen | SR: 62.45 -> 62.71 | No clear effect |
| use instruction generation instead of rephrasing (ablation) | Airbert pretraining · R2R val unseen | SR: 63.35 -> 63.11 | Hurt |
| add wrong trajectories as extra negatives in fine-tuning (ablation) | VLN-BERT · R2R val unseen | SR: 59.26 -> 59.11 | No clear effect |
| add keyword highlighting loss in fine-tuning (ablation) | VLN-BERT · R2R val unseen | SR: 59.26 -> 61.37 | Improved |
| add hard negatives from masked-keyword replacement (ablation) | VLN-BERT · R2R val unseen | SR: 59.26 -> 61.63 | Improved |
| add shuffled visual paths as negatives in fine-tuning (ablation) | VLN-BERT · R2R val unseen | SR: 59.26 -> 61.98 | Improved |
| replace VLN-BERT with Airbert pretraining in ensemble with speaker and follower | Airbert ensemble · R2R val unseen | SR: 73.61 -> 75.01 | Improved |
Later papers that compared with this method
5 later accepted papers report Airbert as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions (NeurIPS 2024 · better on 0 of 2 shared results)
- Learning Vision-and-Language Navigation from YouTube Videos (ICCV 2023 · better on 6 of 6 shared results)
- HOP+: History-Enhanced and Order-Aware Pre-Training for Vision-and-Language Navigation (TPAMI 2023 · better on 4 of 4 shared results)
- HOP: History-and-Order Aware Pre-Training for Vision-and-Language Navigation (CVPR 2022 · better on 2 of 2 shared results)
- Learning from Unlabeled 3D Environments for Vision-and-Language Navigation (ECCV 2022 · better on 1 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Improving Vision-and-Language Navigation with Image-Text Pairs from the Web (ECCV 2020 · similarity 0.92)
- 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 0.91)
- General Scene Adaptation for Vision-and-Language Navigation (ICLR 2025 · similarity 0.89)
- NavBench: Probing Multimodal Large Language Models for Embodied Navigation (NeurIPS 2025 · similarity 0.89)
- Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions (NeurIPS 2024 · similarity 0.88)
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.
