AI Paper Atlas

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

Prioritized Semantic Learning for Zero-shot Instance Navigation

xinyu sun, Lizhao Liu, Hongyan Zhi, Ronghe Qiu, Junwei Liang

ECCV 2024 · Vision-language and multimodal › Robot action and navigation · approach: Pretraining and data augmentation for VLN · 23 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
add entropy-minimized goal view selection to ZSON (ablation)ZSON · InstanceNav image-goalSR: 12.7 -> 14.8Improved
add perspective reward relaxation to a model without the semantic perception module (ablation)ZSON with goal view selection · InstanceNav image-goalSR: 12.7 -> 10.8Hurt
add semantic perception module (SPM) to the agent (ablation)ZSON · InstanceNav image-goalSR: 12.7 -> 19.5Improved
add perspective reward relaxation on top of SPM and goal view selection (ablation)PSL · InstanceNav image-goalSR: 16.5 -> 22.0Improved
add perspective reward relaxation on top of SPM and goal view selection (ablation)PSL · HM3D ObjectNavSR: 35.0 -> 42.4Improved
add SPM and goal view selection together versus goal view selection alone (ablation)PSL · InstanceNav image-goalSR: 12.7 -> 16.5Improved
retrieve and weight image embeddings for text goal (semantic expansion inference) instead of direct text embedding (ablation)PSL · InstanceNav text-goalSR: 6.6 -> 16.5Improved
use ImageNav support set rather than limited-category IIN support set (ablation)semantic expansion inference · InstanceNav text-goalSR: 11.1 -> 12.4Improved
PSL versus LLM-based methods on ObjectNav, without LLM or mappingPSL · HM3D ObjectNavSR: 39.2 -> 42.4Improved
transfer OVRL ImageNav model to text goals via semantic expansionOVRL · InstanceNav text-goalSR: 3.7Hurt
PSL compared with a supervised model on image-goal SPLPSL · InstanceNav image-goalSPL: 11.8 -> 11.4Mixed

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