AI Paper Atlas

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

MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation

Saim Wani, Shivansh Patel, Unnat Jain, Angel Chang, Manolis Savva

NeurIPS 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 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
Use an object-recognition map instead of a simple RNN memoryNavigation agents · MultiON-1, MultiON-2, and MultiON-3Success (%): 62 -> 79; 24 -> 51; 10 -> 22Improved
Use SMT, EgoMap, or FRMQN memory rather than a simple RNN memoryNavigation agents · MultiON-3Success (%): 10 -> 9; 10 -> 16; 10 -> 13Mixed
Automatically call the found action (ablation)OracleMap · MultiON-3Success (%): 48% -> 90%Improved
Remove the reward for coming closer to the goal (ablation)Trained navigation agents · MultiONtraining successHurt
Do not terminate the episode after an incorrect found action (ablation)Trained navigation agents · MultiONtraining successHurt

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