# INSTINCT: Instance-Level Interaction Architecture for Query-Based Collaborative Perception

arXiv: https://arxiv.org/abs/2509.23700 · HTML: https://mlsanity.com/paper/2509.23700/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 40 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Builds on (most cited first, 30 of 31)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [DN-DETR: Accelerate DETR Training by Introducing Query DeNoising](https://mlsanity.com/paper/2203.01305/) (2022)
- [V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer](https://mlsanity.com/paper/2203.10638/) (2022)
- [OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication](https://mlsanity.com/paper/2109.07644/) (2021)
- [V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction](https://mlsanity.com/paper/2008.07519/) (2020)
- [DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection](https://mlsanity.com/paper/2204.05575/) (2022)
- [Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps](https://mlsanity.com/paper/2209.12836/) (2022)
- [CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers](https://mlsanity.com/paper/2207.02202/) (2022)
- [When2com: Multi-Agent Perception via Communication Graph Grouping](https://mlsanity.com/paper/2006.00176/) (2020)
- [V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception](https://mlsanity.com/paper/2303.07601/) (2023)
- [Robust Collaborative 3D Object Detection in Presence of Pose Errors](https://mlsanity.com/paper/2211.07214/) (2022)
- [Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion](https://mlsanity.com/paper/2203.09780/) (2022)
- [Communication-Efficient Collaborative Perception via Information Filling with Codebook](https://mlsanity.com/paper/2405.04966/) (2024)
- [DEIM: DETR with Improved Matching for Fast Convergence](https://mlsanity.com/paper/2412.04234/) (2024)
- [Asynchrony-Robust Collaborative Perception via Bird's Eye View Flow](https://mlsanity.com/paper/2309.16940/) (2023)
- [Transformation-Equivariant 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/2211.11962/) (2022)
- [DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detection](https://mlsanity.com/paper/2312.15742/) (2023)
- [Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection](https://mlsanity.com/paper/2311.01682/) (2023)
- [BoxeR: Box-Attention for 2D and 3D Transformers](https://mlsanity.com/paper/2111.13087/) (2021)
- [QUEST: Query Stream for Practical Cooperative Perception](https://mlsanity.com/paper/2308.01804/) (2023)
- [ConQueR: Query Contrast Voxel-DETR for 3D Object Detection](https://mlsanity.com/paper/2212.07289/) (2022)
- [SEED: A Simple and Effective 3D DETR in Point Clouds](https://mlsanity.com/paper/2407.10749/) (2024)
- [Robust Collaborative Perception without External Localization and Clock Devices](https://mlsanity.com/paper/2405.02965/) (2024)
- [ActFormer: Scalable Collaborative Perception via Active Queries](https://mlsanity.com/paper/2403.04968/) (2024)
- [IFTR: An Instance-Level Fusion Transformer for Visual Collaborative Perception](https://mlsanity.com/paper/2407.09857/) (2024)
- [CoDynTrust: Robust Asynchronous Collaborative Perception via Dynamic Feature Trust Modulus](https://mlsanity.com/paper/2502.08169/) (2025)

## Built on by (most cited first, 5 of 5)

- [Dense Coverage, Sparse Refinement: Byte-Constrained Cooperative Perception](https://mlsanity.com/paper/2609.29456/) (2026)
- [Move What Matters: Parameter-Efficient Domain Adaptation via Optimal Transport Flow for Collaborative Perception](https://mlsanity.com/paper/2602.11565/) (2026)
- [One World, Dual Timeline: Decoupled Spatio-Temporal Gaussian Scene Graph for 4D Cooperative Driving Reconstruction](https://mlsanity.com/paper/2605.07910/) (2026)
- [INTACT: Ego-Guided Typed Sparse Evidence Retrieval for Heterogeneous Collaborative Perception](https://mlsanity.com/paper/2606.04437/) (2026)
- [ViCo3D: Empowering LiDAR-based Collaborative 3D Object Detection with Vision Foundation Models](https://mlsanity.com/paper/2607.12959/) (2026)

## Abstract (arXiv)

Collaborative perception systems overcome single-vehicle limitations in long-range detection and occlusion scenarios by integrating multi-agent sensory data, improving accuracy and safety. However, frequent cooperative interactions and real-time requirements impose stringent bandwidth constraints. Previous works proves that query-based instance-level interaction reduces bandwidth demands and manual priors, however, LiDAR-focused implementations in collaborative perception remain underdeveloped, with performance still trailing state-of-the-art approaches. To bridge this gap, we propose INSTINCT (INSTance-level INteraCtion ArchiTecture), a novel collaborative perception framework featuring three core components: 1) a quality-aware filtering mechanism for high-quality instance feature selection; 2) a dual-branch detection routing scheme to decouple collaboration-irrelevant and collaboration-relevant instances; and 3) a Cross Agent Local Instance Fusion module to aggregate local hybrid instance features. Additionally, we enhance the ground truth (GT) sampling technique to facilitate training with diverse hybrid instance features. Extensive experiments across multiple datasets demonstrate that INSTINCT achieves superior performance. Specifically, our method achieves an improvement in accuracy 13.23%/33.08% in DAIR-V2X and V2V4Real while reducing the communication bandwidth to 1/281 and 1/264 compared to state-of-the-art methods. The code is available at https://github.com/CrazyShout/INSTINCT.