AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation

Ronghao Dang, Lu Chen, Liuyi Wang, Zongtao He, Chengju Liu, Qijun Chen

ICML 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Prompted SAM segmentation · 4 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 search thinking (object association via DOA-style attention) (ablation)MT · AI2-Thor ALLSR: 43.48 -> 75.94Improved
add navigation thinking (ablation)MT · AI2-Thor ALLSR: 75.94 -> 79.62Improved
add exploration thinking (ablation)MT · AI2-Thor ALLSR: 79.62 -> 81.97Improved
add obstacle thinking (ablation)MT · AI2-Thor ALLSR: 81.97 -> 83.14Improved
add multiple thinking collaboration (MTC) module (ablation)MT · AI2-Thor ALLSR: 82.26 -> 83.14Improved
add meta-ability reward R_MA (during first 0.2M episodes) (ablation)MT · AI2-Thor ALLSR and SPL: SR 81.96 -> 83.14; SPL 49.54 -> 50.23Improved
keep meta-ability reward throughout all training episodes (ablation)MT · AI2-Thor ALLSR: 83.14 -> 81.31Hurt
MT decoupled meta-ability model vs DOAMT · AI2-Thor ALLSR and SPL: SR 74.32 -> 83.14; SPL 40.27 -> 50.23Improved
MT decoupled meta-ability model vs DOAMT · RoboTHOR ALLSR and SPL: SR 36.22 -> 42.17; SPL 22.12 -> 29.14Improved
zero-shot MT-ZS with GloVe target similarity instead of one-hotMT-ZS · Zero-shot AI2-Thor unseen 18/4SR: 57.32 (ZSON) -> 68.61Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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