Heterogeneous Model Fusion for Privacy-Aware Multi-Camera Surveillance via Synthetic Domain Adaptation

• URL: http://arxiv.org/abs/2605.02169v2
• Date: Sun, 10 May 2026 01:39:21 GMT
• Title: Heterogeneous Model Fusion for Privacy-Aware Multi-Camera Surveillance via Synthetic Domain Adaptation
• Abstract summary: HeroCrystal is a privacy-preserving framework for multi-camera domain-adaptive object detection.<n>Our framework addresses challenges such as data privacy, class imbalance, and heterogeneous architectures.<n>Our method improves mAP by +2.1% over prior privacy-preserving approaches.
• Score: 9.857691969307828
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We propose HeroCrystal, a novel privacy-preserving framework for multi-camera domain-adaptive object detection, addressing challenges such as data privacy, class imbalance, and heterogeneous architectures. Our framework consists of three key stages. In the Generated Stage, we introduce a one-shot, target-aware diffusion-based generation module that learns visual style from a single target-domain image while leveraging prompt-based control to synthesize specific object instances. Unlike conventional style transfer-based methods that require large target datasets and ignore semantic-level discrepancies, our approach enables privacy-preserving augmentation to reduce ethical concerns, and introduces controllable rare object generation to mitigate long-tailed category degradation. In the Federated Stage, we employ probabilistic Faster R-CNN on the client side to improve localization accuracy, and a dynamic model contrastive strategy to suppress domain-specific bias. The server side performs model fusion across heterogeneous architectures without accessing raw data. Finally, in the Distilled Stage, we propose an inconsistent categories integration algorithm to resolve label inconsistency and architecture heterogeneity across clients. Extensive experiments on multiple cross-domain detection benchmarks demonstrate that our method outperforms existing multi-source domain adaptation and federated learning baselines under multi-class, privacy-preserving settings. Our method improves mAP by +2.1% over prior privacy-preserving approaches and achieves a new state-of-the-art mAP of 33.4%, highlighting the effectiveness of HeroCrystal in enabling practical multi-camera AI surveillance systems. The source code is publicly available at https://github.com/ccuvislab/HeroCrystal.

Related papers

• Prototype-Regularized Federated Learning for Cross-Domain Aspect Sentiment Triplet Extraction [16.84821204487277]
  Aspect Sentiment Triplet Extraction aims to extract all sentiment triplets of aspect terms, opinion terms, and sentiment polarities from a sentence.<n>Existing methods are typically trained on individual datasets in isolation, failing to jointly capture the common feature representations shared across domains.<n>We propose Prototype-based Cross-Domain Span Prototype extraction (PCD-SpanProto) to enable distributed clients to exchange class-level prototypes instead of full model parameters.
  arXiv  Detail & Related papers  (2026-04-10T09:03:44Z)
• FeDecider: An LLM-Based Framework for Federated Cross-Domain Recommendation [75.50721642765994]
  Large language model (LLM)-based recommendation models have demonstrated impressive performance.<n>We propose an LLM-based framework for Federated cross-domain recommendation, FeDecider.<n>Extensive experiments across diverse datasets validate the effectiveness of our proposed FeDecider.
  arXiv  Detail & Related papers  (2026-02-17T21:42:28Z)
• UnifiedFL: A Dynamic Unified Learning Framework for Equitable Federation [5.972927416266618]
  Federated learning has emerged as a key paradigm for collaborative model training across multiple clients without sharing raw data.<n>We propose UnifiedFL, a dynamic federated learning framework that represents heterogeneous local networks as nodes and edges in a directed model graph.
  arXiv  Detail & Related papers  (2025-10-30T11:01:57Z)
• Secure Generalization through Stochastic Bidirectional Parameter Updates Using Dual-Gradient Mechanism [6.03163048890944]
  Federated learning (FL) has gained increasing attention due to privacy-preserving collaborative training on decentralized clients.<n>Recent research has underscored the risk of exposing private data to adversaries, even within FL frameworks.<n>We generate diverse models for each client by using systematic perturbations in model parameters at a fine-grained level.
  arXiv  Detail & Related papers  (2025-04-03T02:06:57Z)
• Object Style Diffusion for Generalized Object Detection in Urban Scene [69.04189353993907]
  We introduce a novel single-domain object detection generalization method, named GoDiff.<n>By integrating pseudo-target domain data with source domain data, we diversify the training dataset.<n> Experimental results demonstrate that our method not only enhances the generalization ability of existing detectors but also functions as a plug-and-play enhancement for other single-domain generalization methods.
  arXiv  Detail & Related papers  (2024-12-18T13:03:00Z)
• FedDUAL: A Dual-Strategy with Adaptive Loss and Dynamic Aggregation for Mitigating Data Heterogeneity in Federated Learning [12.307490659840845]
  Federated Learning (FL) combines locally optimized models from various clients into a unified global model.<n>FL encounters significant challenges such as performance degradation, slower convergence, and reduced robustness of the global model.<n>We introduce an innovative dual-strategy approach designed to effectively resolve these issues.
  arXiv  Detail & Related papers  (2024-12-05T18:42:29Z)
• Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection [14.837853049121687]
  3D object detection leveraging multi-view cameras has demonstrated their practical and economical value in challenging vision tasks. Typical supervised learning approaches face challenges in achieving satisfactory adaptation toward unseen and unlabeled target datasets. We propose Unified Domain Generalization and Adaptation (UDGA), a practical solution to mitigate those drawbacks.
  arXiv  Detail & Related papers  (2024-10-29T18:51:49Z)
• StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization [85.18995948334592]
  Single domain generalization (single DG) aims at learning a robust model generalizable to unseen domains from only one training domain. State-of-the-art approaches have mostly relied on data augmentations, such as adversarial perturbation and style enhancement, to synthesize new data. We propose emphStyDeSty, which explicitly accounts for the alignment of the source and pseudo domains in the process of data augmentation.
  arXiv  Detail & Related papers  (2024-06-01T02:41:34Z)
• Target-Aware Generative Augmentations for Single-Shot Adaptation [21.840653627684855]
  We propose a new approach to adapting models from a source domain to a target domain. SiSTA fine-tunes a generative model from the source domain using a single-shot target, and then employs novel sampling strategies for curating synthetic target data. We find that SiSTA produces significantly improved generalization over existing baselines in face detection and multi-class object recognition.
  arXiv  Detail & Related papers  (2023-05-22T17:46:26Z)
• Generative Domain Adaptation for Face Anti-Spoofing [38.12738183385737]
  Face anti-spoofing approaches based on unsupervised domain adaption (UDA) have drawn growing attention due to promising performances for target scenarios. Most existing UDA FAS methods typically fit the trained models to the target domain via aligning the distribution of semantic high-level features. We propose a novel perspective of UDA FAS that directly fits the target data to the models, stylizes the target data to the source-domain style via image translation, and further feeds the stylized data into the well-trained source model for classification.
  arXiv  Detail & Related papers  (2022-07-20T16:24:57Z)
• Source-Free Open Compound Domain Adaptation in Semantic Segmentation [99.82890571842603]
  In SF-OCDA, only the source pre-trained model and the target data are available to learn the target model. We propose the Cross-Patch Style Swap (CPSS) to diversify samples with various patch styles in the feature-level. Our method produces state-of-the-art results on the C-Driving dataset.
  arXiv  Detail & Related papers  (2021-06-07T08:38:41Z)
• Unsupervised and self-adaptative techniques for cross-domain person re-identification [82.54691433502335]
  Person Re-Identification (ReID) across non-overlapping cameras is a challenging task. Unsupervised Domain Adaptation (UDA) is a promising alternative, as it performs feature-learning adaptation from a model trained on a source to a target domain without identity-label annotation. In this paper, we propose a novel UDA-based ReID method that takes advantage of triplets of samples created by a new offline strategy.
  arXiv  Detail & Related papers  (2021-03-21T23:58:39Z)
• Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID [55.21702895051287]
  Domain adaptive object re-ID aims to transfer the learned knowledge from the labeled source domain to the unlabeled target domain. We propose a novel self-paced contrastive learning framework with hybrid memory. Our method outperforms state-of-the-arts on multiple domain adaptation tasks of object re-ID.
  arXiv  Detail & Related papers  (2020-06-04T09:12:44Z)
• Unsupervised Domain Adaptation in Person re-ID via k-Reciprocal Clustering and Large-Scale Heterogeneous Environment Synthesis [76.46004354572956]
  We introduce an unsupervised domain adaptation approach for person re-identification. Experimental results show that the proposed ktCUDA and SHRED approach achieves an average improvement of +5.7 mAP in re-identification performance.
  arXiv  Detail & Related papers  (2020-01-14T17:43:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.