AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Hierarchical Object-to-Zone Graph for Object Navigation

Sixian Zhang, Xinhang Song, Yubing Bai, Weijie Li, Yakui Chu, Shuqiang Jiang

ICCV 2021 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Vision-language navigation agents · 100 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
train and test with sub-goal zone instead of target zone (ablation)HOZ · AI2-THOR (All)SR: 69.16 -> 70.57Improved
add the object layer to the baseline (ablation)A3C baseline · AI2-THOR (All)SR: 57.35 -> 65.12Improved
add the scene layer on top of the object layer (ablation)A3C + object layer · AI2-THOR (All)SPL: 37.86 -> 38.83Improved
add the zone layer on top of object and scene layers (ablation)A3C + object + scene · AI2-THOR (All)SR: 65.81 -> 70.57Improved
add the done reminder to the object-layer baseline (ablation)A3C + object layer · AI2-THOR (All)SR: 65.12 -> 66.73Improved
add the done reminder to full HOZ (ablation)HOZ · AI2-THOR (All)SPL: 40.84 -> 40.02Hurt
add self-supervised test-time adaptation (TPN) to HOZ (ablation)HOZ · AI2-THOR (All)SR: 70.62 -> 73.15Mixed
add location information to visual features when clustering zones (ablation)HOZ · AI2-THOR (All)SR: -2.40Hurt
use ground-truth object detection instead of pretrained detector (ablation)A3C + object layer · AI2-THOR (All)SPL: 37.86 -> 55.91Improved
use ground-truth object detection instead of pretrained detector (ablation)A3C + object layer · AI2-THOR (All)SR: 65.12 -> 66.78No clear effect
use learned zone nodes instead of random nodes (edges random) (ablation)HOZ · AI2-THOR (All)SR: 67.81 -> 69.33Improved
use learned edges instead of random edges (nodes kept) (ablation)HOZ · AI2-THOR (All)SR: 69.33 -> 70.47Improved

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