# FEDEXCHANGE: Bridging the Domain Gap in Federated Object Detection for Free

arXiv: https://arxiv.org/abs/2509.10503 · HTML: https://mlsanity.com/paper/2509.10503/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Builds on (most cited first, 25 of 25)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [CrowdHuman: A Benchmark for Detecting Human in a Crowd](https://mlsanity.com/paper/1805.00123/) (2018)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [Federated Learning for Smart Healthcare: A Survey](https://mlsanity.com/paper/2111.08834/) (2021)
- [Unbiased Mean Teacher for Cross-domain Object Detection](https://mlsanity.com/paper/2003.00707/) (2020)
- [Cross-Domain Adaptive Teacher for Object Detection](https://mlsanity.com/paper/2111.13216/) (2021)
- [FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clients](https://mlsanity.com/paper/2207.09209/) (2022)
- [Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection](https://mlsanity.com/paper/1905.05396/) (2019)
- [Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector](https://mlsanity.com/paper/2008.08574/) (2020)
- [Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation](https://mlsanity.com/paper/2003.10275/) (2020)
- [Domain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNN](https://mlsanity.com/paper/2007.01571/) (2020)
- [Cross Domain Object Detection by Target-Perceived Dual Branch Distillation](https://mlsanity.com/paper/2205.01291/) (2022)
- [Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detection](https://mlsanity.com/paper/2110.01428/) (2021)
- [SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving](https://mlsanity.com/paper/2106.11118/) (2021)
- [WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild](https://mlsanity.com/paper/1909.12118/) (2019)
- [Multi-level Domain Adaptive learning for Cross-Domain Detection](https://mlsanity.com/paper/1907.11484/) (2019)
- [Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains](https://mlsanity.com/paper/2403.09048/) (2024)
- [Benchmarking Deep Learning Models on NVIDIA Jetson Nano for Real-Time Systems: An Empirical Investigation](https://mlsanity.com/paper/2406.17749/) (2024)
- [COALA: A Practical and Vision-Centric Federated Learning Platform](https://mlsanity.com/paper/2407.16560/) (2024)
- [Addressing Heterogeneity in Federated Learning via Distributional Transformation](https://mlsanity.com/paper/2210.15025/) (2022)

## Abstract (arXiv)

Federated Object Detection (FOD) enables clients to collaboratively train a global object detection model without accessing their local data from diverse domains. However, significant variations in environment, weather, and other domain specific factors hinder performance, making cross domain generalization a key challenge. Existing FOD methods often overlook the hardware constraints of edge devices and introduce local training regularizations that incur high computational costs, limiting real-world applicability. In this paper, we propose FEDEXCHANGE, a novel FOD framework that bridges domain gaps without introducing additional local computational overhead. FEDEXCHANGE employs a server side dynamic model exchange strategy that enables each client to gain insights from other clients' domain data without direct data sharing. Specifically, FEDEXCHANGE allows the server to alternate between model aggregation and model exchange. During aggregation rounds, the server aggregates all local models as usual. In exchange rounds, FEDEXCHANGE clusters and exchanges local models based on distance measures, allowing local models to learn from a variety of domains. As all operations are performed on the server side, clients can achieve improved cross domain utility without any additional computational overhead. Extensive evaluations demonstrate that FEDEXCHANGE enhances FOD performance, achieving 1.6X better mean average precision in challenging domains, such as rainy conditions, while requiring only 0.8X the computational resources compared to baseline methods.