# Background Fades, Foreground Leads: Curriculum-Guided Background Pruning for Efficient Foreground-Centric Collaborative Perception

arXiv: https://arxiv.org/abs/2510.19250 · HTML: https://mlsanity.com/paper/2510.19250/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 32 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Builds on (most cited first, 24 of 24)

- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [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)
- [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)
- [Robust Collaborative 3D Object Detection in Presence of Pose Errors](https://mlsanity.com/paper/2211.07214/) (2022)
- [Cooperative Perception for 3D Object Detection in Driving Scenarios using Infrastructure Sensors](https://mlsanity.com/paper/1912.12147/) (2019)
- [An Extensible Framework for Open Heterogeneous Collaborative Perception](https://mlsanity.com/paper/2401.13964/) (2024)
- [Communication-Efficient Collaborative Perception via Information Filling with Codebook](https://mlsanity.com/paper/2405.04966/) (2024)
- [STAMP: Scalable Task And Model-agnostic Collaborative Perception](https://mlsanity.com/paper/2501.18616/) (2025)
- [CORE: Cooperative Reconstruction for Multi-Agent Perception](https://mlsanity.com/paper/2307.11514/) (2023)
- [CoSDH: Communication-Efficient Collaborative Perception via Supply-Demand Awareness and Intermediate-Late Hybridization](https://mlsanity.com/paper/2503.03430/) (2025)
- [LangCoop: Collaborative Driving with Language](https://mlsanity.com/paper/2504.13406/) (2025)
- [SparseAlign: A Fully Sparse Framework for Cooperative Object Detection](https://mlsanity.com/paper/2503.12982/) (2025)
- [Directed-CP: Directed Collaborative Perception for Connected and Autonomous Vehicles via Proactive Attention](https://mlsanity.com/paper/2409.08840/) (2024)
- [Co-MTP: A Cooperative Trajectory Prediction Framework with Multi-Temporal Fusion for Autonomous Driving](https://mlsanity.com/paper/2502.16589/) (2025)
- [CoopDETR: A Unified Cooperative Perception Framework for 3D Detection via Object Query](https://mlsanity.com/paper/2502.19313/) (2025)
- [ActFormer: Scalable Collaborative Perception via Active Queries](https://mlsanity.com/paper/2403.04968/) (2024)
- [CoDynTrust: Robust Asynchronous Collaborative Perception via Dynamic Feature Trust Modulus](https://mlsanity.com/paper/2502.08169/) (2025)
- [SlimComm: Doppler-Guided Sparse Queries for Bandwidth-Efficient Cooperative 3-D Perception](https://mlsanity.com/paper/2508.13007/) (2025)

## Built on by (most cited first, 1 of 1)

- [LACO: Adaptive Latent Communication for Collaborative Driving](https://mlsanity.com/paper/2605.22504/) (2026)

## Abstract (arXiv)

Collaborative perception enhances the reliability and spatial coverage of autonomous vehicles by sharing complementary information across vehicles, offering a promising solution to long-tail scenarios that challenge single-vehicle perception. However, the bandwidth constraints of vehicular networks make transmitting the entire feature map impractical. Recent methods, therefore, adopt a foreground-centric paradigm, transmitting only predicted foreground-region features while discarding the background, which encodes essential context. We propose FadeLead, a foreground-centric framework that overcomes this limitation by learning to encapsulate background context into compact foreground features during training. At the core of our design is a curricular learning strategy that leverages background cues early on but progressively prunes them away, forcing the model to internalize context into foreground representations without transmitting background itself. Extensive experiments on both simulated and real-world benchmarks show that FadeLead outperforms prior methods under different bandwidth settings, underscoring the effectiveness of context-enriched foreground sharing.