arXiv 2511.080182025-11-11cs.CV

用于想象监督目标检测的高质量提案编码与级联去噪

High-Quality Proposal Encoding and Cascade Denoising for Imaginary Supervised Object Detection

Institute of Cyberspace Security, Harbin Institute of Technology, Shenzhen（网络安全研究所，哈尔滨工业大学，深圳）；Department of New Networks, Peng Cheng Laboratory（新网络部门，鹏城实验室）；School of Cyberspace Science, Harbin Institute of Technology（空间科学学院，哈尔滨工业大学）；Center on Machine Learning Research, Harbin Institute of Technology（机器学习研究中心，哈尔滨工业大学）；Faculty of Information Technology, Monash University（信息技术学院，墨尔本大学）

Zhiyuan Chen, Yuelin Guo, Zitong Huang, Haoyu He, Renhao Lu, Weizhe Zhang

备注：: This work has been submitted to Pattern Recognition for possible publication

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对想象监督目标检测（ISOD）中合成数据质量低、DETR检测器收敛慢及去噪压力不均等问题，提出级联HQP-DETR，通过高质量提案编码和动态级联去噪，在真实场景取得SOTA性能并验证架构普适性。

摘要：

目标检测模型需要大规模标注数据集，而创建此类数据集成本高且劳动密集，这推动了想象监督目标检测（ISOD）的发展，即模型在合成图像上训练、在真实图像上测试。但现有方法存在三个局限：（1）合成数据集面临提示简单、图像质量差和弱监督问题；（2）基于DETR的检测器因随机查询初始化，存在收敛慢和过拟合合成模式的问题，阻碍了真实场景泛化；（3）均匀去噪压力会加剧模型对伪标签噪声的过拟合。我们提出级联HQP-DETR来解决这些问题：首先，引入基于LLaMA-3、Flux和Grounding DINO的高质量数据管道，生成FluxVOC和FluxCOCO数据集，将ISOD从弱监督推进到全监督；其次，高质量提案引导的查询编码利用SAM生成的提案和RoI池化特征初始化目标查询，加速收敛并避免模型过拟合合成模式；第三，级联去噪算法通过在解码器层逐步提高IoU阈值动态调整训练权重，引导模型从可靠视觉线索学习鲁棒边界，而非过拟合噪声标签。仅在FluxVOC上训练12个epoch后，级联HQP-DETR在PASCAL VOC 2007上达到61.04%的SOTA mAP@0.5，优于强基线，其优异的真实数据性能验证了该架构的普遍适用性。

英文摘要：

Object detection models demand large-scale annotated datasets, which are costly and labor-intensive to create. This motivated Imaginary Supervised Object Detection (ISOD), where models train on synthetic images and test on real images. However, existing methods face three limitations: (1) synthetic datasets suffer from simplistic prompts, poor image quality, and weak supervision; (2) DETR-based detectors, due to their random query initialization, struggle with slow convergence and overfitting to synthetic patterns, hindering real-world generalization; (3) uniform denoising pressure promotes model overfitting to pseudo-label noise. We propose Cascade HQP-DETR to address these limitations. First, we introduce a high-quality data pipeline using LLaMA-3, Flux, and Grounding DINO to generate the FluxVOC and FluxCOCO datasets, advancing ISOD from weak to full supervision. Second, our High-Quality Proposal guided query encoding initializes object queries with image-specific priors from SAM-generated proposals and RoI-pooled features, accelerating convergence while steering the model to learn transferable features instead of overfitting to synthetic patterns. Third, our cascade denoising algorithm dynamically adjusts training weights through progressively increasing IoU thresholds across decoder layers, guiding the model to learn robust boundaries from reliable visual cues rather than overfitting to noisy labels. Trained for just 12 epochs solely on FluxVOC, Cascade HQP-DETR achieves a SOTA 61.04\% mAP@0.5 on PASCAL VOC 2007, outperforming strong baselines, with its competitive real-data performance confirming the architecture's universal applicability.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。