AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative Perception

Weize Li, Yang Li, Quan Yuan, Xiaoyuan Fu, Guiyang Luo, Jinglin Li

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 0 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 causal intervention (MGI-SPD with causal metric learning) (ablation)CauseCollab · OPV2V (Lpp4+CEff+Lsd1+CRes)AP@30: 0.969 -> 0.978Improved
add semantic mask generator to the intervention (ablation)CauseCollab · OPV2V (Lpp4+CEff+Lsd1+CRes)AP@30: 0.972 -> 0.978Improved
add semantic context guidance to the unified converter (ablation)CauseCollab · OPV2V (Lpp4+CEff+Lsd1+CRes)AP@30: 0.837 -> 0.978Improved
use CGDR instead of a ConvNeXt of same depth (ablation)CauseCollab · OPV2V (Lpp4+CEff+Lsd1+CRes)AP@30: 0.972 -> 0.978Improved
use SCE + CGDR instead of a ConvNeXt of same depth (ablation)CauseCollab · OPV2V (Lpp4+CEff+Lsd1+CRes)AP@30: 0.968 -> 0.978Improved
add lightweight adapters for new modalities (ablation)CauseCollab · OPV2V (Lpp4+CEff+Lsd1+CRes)AP@30: 0.909 -> 0.978Improved
use CauseCollab instead of STAMP under large modality gapheterogeneous collaborative perception · OPV2V large gap (ego CEff, neighbor CRes)AP@30: 0.730 -> 0.772Improved
use CauseCollab instead of prior methods with small modality gapheterogeneous collaborative perception · OPV2V (ego Lpp4, neighbor CEff)AP@30: 0.961 -> 0.971 (STAMP)Improved
use CauseCollab instead of baselines on DAIR-V2Xheterogeneous collaborative perception · DAIR-V2X (Lpp4 ego, CEff neighbor) AP@50AP@50: 0.738 (PnPDA) vs 0.733Mixed
adapt to new modality with CauseCollab adapters instead of baseline adaptationCauseCollab · OPV2V new modalitiestrainable parameters (MB): 1.18 (STAMP) -> 0.68Improved

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