AI Paper Atlas

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

Align before Collaborate: Mitigating Feature Misalignment for Robust Multi-Agent Perception

Dingkang Yang, Dingkang Yang, Ke Li, Dongling Xiao, Zedian Shao, Peng Sun, Liang Song

ECCV 2024 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Collaborative multi-agent perception · 6 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 NEAT plugin to five collaborative perception modelsF-Cooper, CORE, AttFuse, Where2comm, CoBEVT · V2XSet, OPV2V, V2V4Real, OPV2V Culver CityAP@0.7: average gains 8.85%, 4.10%, 6.50%, 3.81%, 8.78%Improved
add NEAT to F-CooperF-Cooper · OPV2V Culver CityAP@0.7: 48.02 -> 53.28 AP@0.7; 68.68 -> 74.91 AP@0.5Improved
add NEAT to AttFuse on OPV2VAttFuse · OPV2VAP@0.7: 59.82 -> 68.19Improved
use NEAT instead of SyncNet or CoAlign plugins on CoBEVTCoBEVT · V2XSetAP@0.7: 60.20 (CoAlign) -> 65.16Improved
add deformable feature aggregation (FA) to CoBEVT (ablation)CoBEVT + NEAT · V2XSetAP@0.7: 54.30 -> 58.24Improved
add object-related token generation (TG) (ablation)CoBEVT + NEAT · V2XSetAP@0.7: 58.24 -> 59.97Improved
add importance map generation (MG) (ablation)CoBEVT + NEAT · V2XSetAP@0.7: 59.97 -> 62.08Improved
add query proposal selection (PS) (ablation)CoBEVT + NEAT · V2XSetAP@0.7: 62.08 -> 63.25Improved
add region cross-attention reinforcement (RCR) (ablation)CoBEVT + NEAT · V2XSetAP@0.7: 63.25 -> 65.16Improved
add NEAT to vanilla methods under increasing transmission delayF-Cooper, AttFuse, Where2comm, CoBEVT · OPV2VAP@0.7Improved
add NEAT to vanilla methods under increasing localization errorF-Cooper, AttFuse, Where2comm, CoBEVT · V2XSetAP@0.7Improved

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