# What Makes Good Collaborative Views? Contrastive Mutual Information Maximization for Multi-Agent Perception

arXiv: https://arxiv.org/abs/2403.10068 · HTML: https://mlsanity.com/paper/2403.10068/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 15 Mar 2024.

## Builds on (most cited first, 21 of 21)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization](https://mlsanity.com/paper/1606.00709/) (2016)
- [V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer](https://mlsanity.com/paper/2203.10638/) (2022)
- [V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction](https://mlsanity.com/paper/2008.07519/) (2020)
- [Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps](https://mlsanity.com/paper/2209.12836/) (2022)
- [Learning Distilled Collaboration Graph for Multi-Agent Perception](https://mlsanity.com/paper/2111.00643/) (2021)
- [Cooper: Cooperative Perception for Connected Autonomous Vehicles based on 3D Point Clouds](https://mlsanity.com/paper/1905.05265/) (2019)
- [When2com: Multi-Agent Perception via Communication Graph Grouping](https://mlsanity.com/paper/2006.00176/) (2020)
- [V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Driving](https://mlsanity.com/paper/2202.08449/) (2022)
- [V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception](https://mlsanity.com/paper/2303.07601/) (2023)
- [Who2com: Collaborative Perception via Learnable Handshake Communication](https://mlsanity.com/paper/2003.09575/) (2020)
- [COOPERNAUT: End-to-End Driving with Cooperative Perception for Networked Vehicles](https://mlsanity.com/paper/2205.02222/) (2022)
- [Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learning](https://mlsanity.com/paper/2006.02598/) (2020)
- [Bridging the Domain Gap for Multi-Agent Perception](https://mlsanity.com/paper/2210.08451/) (2022)
- [CORE: Cooperative Reconstruction for Multi-Agent Perception](https://mlsanity.com/paper/2307.11514/) (2023)

## Built on by (most cited first, 11 of 11)

- [CP-Guard: Malicious Agent Detection and Defense in Collaborative Bird's Eye View Perception](https://mlsanity.com/paper/2412.12000/) (2024)
- [UVCPNet: A UAV-Vehicle Collaborative Perception Network for 3D Object Detection](https://mlsanity.com/paper/2406.04647/) (2024)
- [CoDynTrust: Robust Asynchronous Collaborative Perception via Dynamic Feature Trust Modulus](https://mlsanity.com/paper/2502.08169/) (2025)
- [CoDTS: Enhancing Sparsely Supervised Collaborative Perception with a Dual Teacher-Student Framework](https://mlsanity.com/paper/2412.08344/) (2024)
- [InScope: A New Real-world 3D Infrastructure-side Collaborative Perception Dataset for Open Traffic Scenarios](https://mlsanity.com/paper/2407.21581/) (2024)
- [JigsawComm: Joint Semantic Feature Encoding and Transmission for Communication-Efficient Cooperative Perception](https://mlsanity.com/paper/2511.17843/) (2025)
- [Is Intermediate Fusion All You Need for UAV-based Collaborative Perception?](https://mlsanity.com/paper/2504.21774/) (2025)
- [CP-uniGuard: A Unified, Probability-Agnostic, and Adaptive Framework for Malicious Agent Detection and Defense in Multi-Agent Embodied Perception Systems](https://mlsanity.com/paper/2506.22890/) (2025)
- [CoDS: Enhancing Collaborative Perception in Heterogeneous Scenarios via Domain Separation](https://mlsanity.com/paper/2510.13432/) (2025)
- [CoPAD : Multi-source Trajectory Fusion and Cooperative Trajectory Prediction with Anchor-oriented Decoder in V2X Scenarios](https://mlsanity.com/paper/2509.15984/) (2025)
- [WaveComm: Lightweight Communication for Collaborative Perception via Wavelet Feature Distillation](https://mlsanity.com/paper/2603.13365/) (2026)

## Abstract (arXiv)

Multi-agent perception (MAP) allows autonomous systems to understand complex environments by interpreting data from multiple sources. This paper investigates intermediate collaboration for MAP with a specific focus on exploring "good" properties of collaborative view (i.e., post-collaboration feature) and its underlying relationship to individual views (i.e., pre-collaboration features), which were treated as an opaque procedure by most existing works. We propose a novel framework named CMiMC (Contrastive Mutual Information Maximization for Collaborative Perception) for intermediate collaboration. The core philosophy of CMiMC is to preserve discriminative information of individual views in the collaborative view by maximizing mutual information between pre- and post-collaboration features while enhancing the efficacy of collaborative views by minimizing the loss function of downstream tasks. In particular, we define multi-view mutual information (MVMI) for intermediate collaboration that evaluates correlations between collaborative views and individual views on both global and local scales. We establish CMiMNet based on multi-view contrastive learning to realize estimation and maximization of MVMI, which assists the training of a collaboration encoder for voxel-level feature fusion. We evaluate CMiMC on V2X-Sim 1.0, and it improves the SOTA average precision by 3.08% and 4.44% at 0.5 and 0.7 IoU (Intersection-over-Union) thresholds, respectively. In addition, CMiMC can reduce communication volume to 1/32 while achieving performance comparable to SOTA. Code and Appendix are released at https://github.com/77SWF/CMiMC.