AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

Scaling Data Generation in Vision-and-Language Navigation

Zun Wang, Jialu Li, Yicong Hong, Yi Wang, Qi Wu, Mohit Bansal, Stephen Gould, Hao Tan, Yu Qiao

ICCV 2023 · Vision-language and multimodal › Robot action and navigation · approach: Pretraining and data augmentation for VLN · 98 citations (OpenAlex)

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 changedWhereMeasuredEffect
use dense, fully traversable navigation graphs instead of AutoVLN graphs (ablation)DUET on R2R · R2R val-unseenSR: 72.75 -> 76.01Improved
increase number of augmented scenes from 200 to 800 at 700k samples (ablation)DUET on R2R · R2R val-unseenSR: 74.84 -> 76.25Improved
increase samples per scene from 700k to 2890k with 800 scenes (ablation)DUET on R2R · R2R val-unseenSR: 76.25 -> 76.59Improved
recover faulty rendered images in augmented data (ablation)Gibson augmented data · R2R val-unseenSR: 76.33 -> 78.08Improved
add Gibson scenes with faulty images to HM3D data (ablation)DUET on R2R · R2R val-unseenSR: 76.59 -> 76.33No clear effect
use EnvDrop LSTM speaker instead of fine-tuned GPT-2 for instructions (ablation)DUET on R2R · R2R val-unseenSR: 75.82 -> 76.59Improved
keep augmented HM-E data in fine-tuning (ablation)DUET on R2R · R2R val-unseenSR: 76.59 -> 79.10Improved
include PREV data in fine-tuning (ablation)DUET on R2R · R2R val-unseenSR: 79.10 -> 77.10Hurt
add MLM and SAP pre-training tasks (ablation)DUET on R2R · R2R val-unseenSR: 62.62 -> 76.59Improved
add MRM to MLM and SAP pre-training (ablation)DUET on R2R · R2R val-unseenSR: 76.59 -> 75.82Hurt
pre-train with ScaleVLN data in addition to R2R and PREV (no fine-tune) (ablation)DUET · R2R val-unseenSR: 47.42 -> 57.00Improved
scale up with ScaleVLN data on REVERIEDUET · REVERIE test-unseenSR: 52.51 -> 56.13Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy