Research map / Vision-language and multimodal / Cross-modal learning
SiMO: Single-Modality-Operable Multimodal Collaborative Perception
Jiageng Wen, Shengjie Zhao, Bing Li, Jiafeng Huang, Kenan Ye, Hao Deng
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add RD fine-tuning (ablation) | SiMO-PF · OPV2V-H, LiDAR-only | AP@70: 0.26 -> 0.94 | Improved |
| add RD fine-tuning (ablation) | SiMO-PF · OPV2V-H, camera-only | AP@70: 0 -> 0.45 | Improved |
| add LAMMA fusion in place of BEVFusion fusion (both with RD) (ablation) | SiMO-PF · OPV2V-H, LiDAR-only | AP@70: 0.72 -> 0.94 | Improved |
| add LAMMA fusion in place of BEVFusion fusion (both with RD) (ablation) | SiMO-PF · OPV2V-H, camera-only | AP@70: 0 -> 0.45 | Improved |
| add Pretrain-Align-Fuse learning strategy instead of naive joint training (ablation) | SiMO-PF · OPV2V-H, LiDAR-only | AP@70: 0.01 -> 0.26 | Improved |
| add RD fine-tuning to naive joint training (ablation) | SiMO-PF naive · OPV2V-H, L+C | AP@70: 0.94 -> 0.11 | Hurt |
| add LAMMA alignment (ablation) | SiMO · Procrustes disparity cam vs lidar | disparity: 0.6747 -> 0.0472 | Improved |
| add LAMMA alignment (ablation) | SiMO · Procrustes disparity cam vs fused | disparity: 0.3886 -> 0.0215 | Improved |
| add SiMO-AF training to AttFusion, camera-only | SiMO-AF vs AttFusion · OPV2V-H, camera-only | AP@70: 25.30 -> 22.59 | No clear effect |
| use SiMO-PF instead of Pyramid Fusion for camera-only | SiMO-PF vs HEAL · OPV2V-H, camera-only | AP@30: 68.45 -> 80.81 | Improved |
| use SiMO-PF instead of HEAL under heterogeneous failure, camera ego | SiMO-PF vs HEAL · OPV2V-H, C-ego | AP@70: 0.72 -> 0.70 | No clear effect |
| use SiMO-PF instead of HEAL under heterogeneous failure, camera ego | SiMO-PF vs HEAL · OPV2V-H, C-ego | AP@30: 0.85 -> 0.89 | Improved |
Closest papers by meaning
- What to align in multimodal contrastive learning? (ICLR 2025 · similarity 0.86)
- An Extensible Framework for Open Heterogeneous Collaborative Perception (ICLR 2024 · similarity 0.86)
- AirCopBench: A Benchmark for Multi-drone Collaborative Embodied Perception and Reasoning (AAAI 2026 · similarity 0.86)
- Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs (NeurIPS 2024 · similarity 0.86)
- What Makes Good Collaborative Views? Contrastive Mutual Information Maximization for Multi-Agent Perception (AAAI 2024 · similarity 0.85)
- When to Align, When to Predict: A Phase Diagram for Multimodal Learning (NeurIPS 2026 · similarity 0.85)
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.
