D-FINE-seg实现高效实例分割，支持多后端部署
D-FINE-seg: Object Detection and Instance Segmentation Framework with multi-backend deployment
- 基于D-FINE扩展轻量掩码头，融合多种监督策略提升分割精度
- 在TACO数据集上超越YOLO26的F1分数，延迟保持竞争力
- 支持ONNX/TensorRT/OpenVINO全链路优化，适配工业级部署
基于Transformer的实时目标检测器在准确率与延迟间表现优异，D-FINE是其中性能领先的架构之一。然而，基于Transformer的实时实例分割仍较罕见。本文提出D-FINE-seg，作为D-FINE的实例分割扩展，引入轻量级掩码头、分割感知训练（包含框裁剪BCE与Dice损失）、辅助与去噪掩码监督，以及改进的匈牙利匹配代价。在统一TensorRT FP16端到端评测协议下，D-FINE-seg在TACO数据集上相比Ultralytics YOLO26取得更高F1分数，同时保持竞争性延迟。第二贡献是构建了从训练、导出到优化推理的端到端流程，支持ONNX、TensorRT、OpenVINO三种后端，覆盖目标检测与实例分割任务。代码已开源，采用Apache-2.0许可。项目地址：https://github.com/ArgoHA/D-FINE-seg。
原文摘要 · Abstract (English)
Transformer-based real-time object detectors achieve strong accuracy-latency trade-offs, and D-FINE is among the top-performing recent architectures. However, real-time instance segmentation with transformers is still less common. We present D-FINE-seg, an instance segmentation extension of D-FINE that adds: a lightweight mask head, segmentation-aware training, including box cropped BCE and dice mask losses, auxiliary and denoising mask supervision, and adapted Hungarian matching cost. On the TACO dataset, D-FINE-seg improves F1-score over Ultralytics YOLO26 under a unified TensorRT FP16 end-to-end benchmarking protocol, while maintaining competitive latency. Second contribution is an end-to-end pipeline for training, exporting, and optimized inference across ONNX, TensorRT, OpenVINO for both object detection and instance segmentation tasks. This framework is released as open-source under the Apache-2.0 license. GitHub repository - https://github.com/ArgoHA/D-FINE-seg.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。