AI Paper Atlas

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

Learning from Unlabeled 3D Environments for Vision-and-Language Navigation

Shizhe Chen, Pierre-Louis Guhur, Makarand Tapaswi, Cordelia Schmid, Ivan Laptev

ECCV 2022 · Vision-language and multimodal › Robot action and navigation · approach: Pretraining and data augmentation for VLN · 46 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
pretrain DUET on HM3D-AutoVLNDUET · REVERIE val unseenSPL: 33.73 -> 40.85Improved
pretrain DUET on HM3D-AutoVLNDUET · SOON val unseenSPL: 22.58 -> 30.69Improved
add HM3D-AutoVLN pretraining over REVERIE-only training (ablation)DUET · REVERIE val unseenSPL: 30.79 -> 39.36Improved
fine-tune jointly on HM3D-AutoVLN and REVERIE rather than REVERIE only (ablation)DUET · REVERIE val unseenSR: 50.87 -> 55.89Improved
add speaker data from ground-truth annotations on seen buildings (ablation)DUET · REVERIE val unseenSPL: 30.79 -> 33.73Improved
increase HM3D environments from 200 to 900 (ablation)DUET · REVERIE val unseenSPL: 37.65 -> 40.85Improved
use 900 environments instead of 400 at fixed 99,224 instructions (ablation)DUET · REVERIE val unseenSPL: 36.79 -> 38.35Improved
raise object distance limit d_o from 2 m to 3 m (ablation)DUET · REVERIE val unseenSPL: 40.85 -> 40.38Hurt
remove object distance limit (d_o infinite) (ablation)DUET · REVERIE val unseenSPL: 40.85 -> 38.03Hurt
use GPT-2 speaker instead of sentence-template instructions (ablation)DUET · REVERIE val unseenSR: 52.20 -> 55.89Improved
use GPT-2 speaker instead of LSTM speaker (ablation)DUET · REVERIE val unseenSR: 49.59 -> 55.89Improved
merge 2D predictions with cross-view consistency in 3D (ablation)Mask2Former pseudo labels · 300 manually labeled boxeslabel accuracy (%): 37.4 -> 58.3Improved

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