Research map / Multi-agent systems and games / Human-AI and goal-conditioned
GT-Space: Enhancing Heterogeneous Collaborative Perception with Ground Truth Feature Space
Wentao Wang, Haoran Xu, Guang Tan
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 |
|---|---|---|---|
| remove feature projector (ablation) | GT-Space · OPV2V Agent 1 | mAP@70: 0.683 -> 0.814 | Improved |
| remove feature projector (ablation) | GT-Space · V2XSet Agent 1 | mAP@70: 0.604 -> 0.806 | Improved |
| add combinatorial contrastive loss (ablation) | GT-Space · OPV2V Agent 1 | mAP@70: 0.721 -> 0.814 | Improved |
| add combinatorial contrastive loss (ablation) | GT-Space · V2XSet Agent 1 | mAP@70: 0.709 -> 0.806 | Improved |
| use ground-truth feature space instead of PointPillar feature space (ablation) | GT-Space · OPV2V Agent 1 | mAP@70: 0.795 -> 0.814 | Improved |
| use ground-truth feature space instead of PointPillar feature space (ablation) | GT-Space · V2XSet Agent 1 | mAP@50: 0.830 -> 0.873 | Improved |
| use GT-Space instead of STAMP for LiDAR ego with camera collaborator | collaborative perception · OPV2V A1+A3 | AP@70: 0.734 -> 0.766 | Improved |
| use GT-Space instead of HEAL for LiDAR ego with LiDAR collaborator | collaborative perception · OPV2V A1+A2 | AP@70: 0.801 -> 0.810 | Improved |
| use GT-Space instead of STAMP on V2XSet camera pair | collaborative perception · V2XSet A1+A3 | AP@70: 0.703 -> 0.741 | Improved |
| add communication latency up to 500 ms | GT-Space · OPV2V | detection accuracy | No clear effect |
| add Gaussian pose noise | GT-Space · OPV2V | detection accuracy | No clear effect |
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.
- STAMP — STAMP: Scalable Task- And Model-agnostic Collaborative Perception (ICLR 2025) · better on 8 of 8 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
- An Extensible Framework for Open Heterogeneous Collaborative Perception (ICLR 2024 · similarity 0.90)
- STAMP: Scalable Task- And Model-agnostic Collaborative Perception (ICLR 2025 · similarity 0.90)
- One is Plenty: A Polymorphic Feature Interpreter for Immutable Heterogeneous Collaborative Perception (CVPR 2025 · similarity 0.90)
- Pragmatic Heterogeneous Collaborative Perception via Generative Communication Mechanism (NeurIPS 2025 · similarity 0.89)
- CoSDH: Communication-Efficient Collaborative Perception via Supply-Demand Awareness and Intermediate-Late Hybridization (CVPR 2025 · similarity 0.88)
- Privacy-Preserving V2X Collaborative Perception Integrating Unknown Collaborators (AAAI 2025 · similarity 0.88)
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.
