AI Paper Atlas

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

Linking Modality Isolation in Heterogeneous Collaborative Perception

Changxing Liu, Zichen Chao, Siheng Chen

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 2 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
modality isolation of m1 and m6 in training data (vs non-isolated) (ablation)Pyramid Fusion · OPV2V m1 + m6AP70: 80.88 -> 65.67Hurt
add codebook to end-to-end training (ablation)Pyramid Fusion · OPV2V m1 + m6 groupAP70: 80.44 -> 77.87Hurt
freeze encoder and add adapter after codebook (ablation)CodeAlign · OPV2V m1 + m6 groupAP30/AP70: AP30 89.54 -> 88.37; AP70 77.87 -> 78.09Mixed
add similarity loss L_sim (ablation)CodeAlign group code space · OPV2V m1 + m6 groupAP70: 78.09 -> 79.63Improved
use Instance similarity loss instead of none (ablation)CodeAlign group code space · OPV2V m1 + m6 groupAP70: 78.09 -> 76.08Hurt
use group code space construction instead of FCF translation for non-isolated modalities (ablation)CodeAlign · OPV2V m1 + m6AP70: 72.92 -> 79.63Improved
translate dense-to-code instead of code-to-code (ablation)CodeAlign translator · OPV2V m1 + m6AP70: 55.16 -> 73.47Improved
translate dense-to-code instead of dense-to-dense (ablation)CodeAlign translator · OPV2V m1 + m6AP70: 75.04 -> 73.47Hurt
use multi-head translator instead of one-to-one (ablation)CodeAlign · OPV2V 4 isolated modalitiesAP50: 88.61 -> 88.51No clear effect
increase codebook size from 4 to 16 (ablation)CodeAlign · OPV2V m1 + m6AP70: 66.30 -> 73.47Improved
increase codebook size from 16 to 64 (ablation)CodeAlign · OPV2V m1 + m6AP70: 73.47 -> 74.56No clear effect
train translator on single-agent data instead of collaborative data (ablation)CodeAlign · OPV2V m1 + m2AP50: 94.88 -> 94.24No 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