AI Paper Atlas

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

Seeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigation

Medhini Narasimhan, Erik Wijmans, Xinlei Chen, Trevor Darrell, Dhruv Batra, Devi Parikh, Amanpreet Singh

ECCV 2020 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Vision-language navigation agents · 57 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 point prediction and point navigation to map-based room policy (ablation)Map Generation + Room Navigation Policy · RoomNav validationRoomNav SPL: 0.16 -> 0.31Improved
add map generation to point prediction + PointNav (ablation)Point prediction + PointNav · RoomNav validationRoomNav SPL: 0.17 -> 0.31Improved
add map generation to point prediction + PointNav with fine-tuning (ablation)Point prediction + PointNav + Fine-tune · RoomNav validationRoomNav SPL: 0.21 -> 0.35Improved
add fine-tuning of point navigation policy on predicted points (ablation)Map Generation + Point Prediction + PointNav · RoomNav validationRoomNav SPL: 0.31 -> 0.35Improved
add fine-tuning of point navigation policy on predicted points (ablation)Point prediction + PointNav · RoomNav validationRoomNav SPL: 0.17 -> 0.21Improved
add semantic maps and point navigation instead of vanilla RL policy (ablation)Vanilla Room Navigation Policy · RoomNav validationRoomNav SPL: 0.10 -> 0.35Improved
add recurrent memory (LSTM) to map generator (ablation)CNN mapper · Map generationmIoU: 25.66 -> 32.92Improved
feed previous semantic maps as input to LSTM mapper (ablation)LSTM(no maps) · Map generationmIoU: 32.92 -> 41.45Improved
feed previous semantic maps as input to LSTM mapper (ablation)LSTM(no maps) · Map generationAverage pixel accuracy: 33.59 -> 43.39Improved
replace predicted maps with ground truth mapsMap Generation + Point Prediction + PointNav · RoomNav validationRoomNav SPL: 0.31 -> 0.61Improved
replace predicted maps with ground truth maps in point predictorPoint prediction MLP · Point predictionError (%): 39.13 -> 22.91Improved
replace predicted point with ground truth pointPointNav · RoomNav validationRoomNav SPL: 0.35 -> 0.83Improved

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