{"slug": "qfedpolyp-a-communication-and-inference-efficient-federated-learning-framework", "title": "QFedPolyp: A Communication- and Inference-Efficient Federated Learning Framework for Polyp Segmentation", "summary": "A new federated learning framework called QFedPolyp, proposed by researchers, combines quantization-aware training with low-precision model communication to reduce transmission costs by approximately 4 times while preserving competitive segmentation accuracy for polyp segmentation. The framework achieves Dice scores of 0.910 on Kvasir-SEG and 0.930 on CVC-ClinicVideoDB, and quantized models achieve up to 1.5 times faster inference than full-precision models, enabling privacy-preserving collaborative polyp segmentation suitable for real-time clinical deployment.", "body_md": "arXiv:2607.22743v1 Announce Type: new\nAbstract: Background and Objective: Automatic polyp segmentation supports computer-aided diagnosis and early colorectal cancer detec- tion. Centralized deep learning requires hospitals to share sensitive medical data, while federated learning preserves privacy but introduces high communication costs through repeated transmission of full-precision model parameters. We propose QFedPolyp, a communication- and inference-efficient federated learning framework for collaborative polyp segmentation.\nMethods: QFedPolyp combines quantization-aware training with low-precision model communication. Each hospital locally trains a lightweight U-Net on private data while simulating quantization during training. Clients transmit quantized model parameters to a central server, where they are reconstructed and aggregated using Federated Averaging. Evaluation is performed on Kvasir-SEG, CVC-ClinicVideoDB, PolypGen, and BKAI-IGH NeoPolyp.\nResults: Full-precision federated training achieves Dice scores of 0.910 on Kvasir-SEG and 0.930 on CVC-ClinicVideoDB. Uni- form 8-bit communication reduces transmission cost by approximately 4 times while preserving competitive segmentation accuracy. Quantized models also achieve up to 1.5 times faster inference than full-precision models.\nConclusions: QFedPolyp enables privacy-preserving collaborative polyp segmentation with reduced communication overhead and faster inference. The resulting lightweight models are suitable for real-time clinical deployment.", "url": "https://wpnews.pro/news/qfedpolyp-a-communication-and-inference-efficient-federated-learning-framework", "canonical_source": "https://arxiv.org/abs/2607.22743", "published_at": "2026-07-28 04:00:00+00:00", "updated_at": "2026-07-28 04:12:21.296141+00:00", "lang": "en", "topics": ["machine-learning", "artificial-intelligence", "ai-research"], "entities": ["QFedPolyp", "U-Net", "Kvasir-SEG", "CVC-ClinicVideoDB", "PolypGen", "BKAI-IGH NeoPolyp"], "alternates": {"html": "https://wpnews.pro/news/qfedpolyp-a-communication-and-inference-efficient-federated-learning-framework", "markdown": "https://wpnews.pro/news/qfedpolyp-a-communication-and-inference-efficient-federated-learning-framework.md", "text": "https://wpnews.pro/news/qfedpolyp-a-communication-and-inference-efficient-federated-learning-framework.txt", "jsonld": "https://wpnews.pro/news/qfedpolyp-a-communication-and-inference-efficient-federated-learning-framework.jsonld"}}