AI Paper Atlas

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

MoDA: Map Style Transfer for Self-Supervised Domain Adaptation of Embodied Agents

Eun Sun Lee, Junho Kim, SangWon Park, Young Min Kim

ECCV 2022 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Vision-language navigation agents · 5 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 flip consistency loss to the pretrained agent (ablation)NA · Gibson speckle noise + dynamics (generalization), ablationPointNav success: 0.12 -> 0.20Improved
add ego style transfer loss on top of flip consistency (ablation)MoDA · Gibson speckle noise + dynamics (generalization), ablationego map MSE: 1.12 -> 1.08Improved
add temporal consistency loss (ablation)MoDA · Gibson speckle noise + dynamics (generalization), ablationPointNav success: 0.20 -> 0.42Improved
add temporal consistency loss (ablation)MoDA · Gibson speckle noise + dynamics (generalization), ablationrotation error (deg): 14.98 -> 3.16Improved
add global style transfer loss (ablation)MoDA · Gibson speckle noise + dynamics (generalization), ablationPointNav success: 0.42 -> 0.56Improved
add global style transfer loss (ablation)MoDA · Gibson speckle noise + dynamics (generalization), ablationrotation error (deg): 3.16 -> 2.61Improved
apply MoDA adaptationNA · Gibson speckle noise + dynamics (generalization)PointNav success: 0.12 -> 0.56Improved
apply MoDA instead of GMC on Matterport3DGMC · Matterport3D large scale + dynamics (generalization)PointNav success: 0.10 -> 0.22Improved
apply MoDA instead of GMC in specializationGMC · Gibson speckle noise + dynamics (specialization)PointNav success: 0.44 -> 0.56Improved
adapt with PAD (rotation prediction + dynamics)NA · Gibson speckle noise + dynamics (generalization)PointNav success: 0.12 -> 0.08Hurt
adapt with PADNA · Gibson speckle noise + dynamics (generalization)rotation error (deg): 15.02 -> 1.08Improved
apply domain randomization with ground-truth supervisionNA · Gibson low-lighting + dynamics (generalization)PointNav success: 0.22 -> 0.20No clear effect

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