SparseDet：通过伪正例挖掘改进稀疏标注目标检测
SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining
AI总结：
针对稀疏标注下目标检测因伪标签噪声导致高稀疏度时性能下降的问题，提出SparseDet方法，通过伪正例挖掘区分标注与未标注区域，结合自监督处理未标注区域，在多个数据集上取得SOTA并构建标准化基准。
摘要：
众所周知，采用稀疏标注进行训练会降低目标检测器的性能。以往的方法聚焦于以未标注框的伪标签形式，为缺失的真实标注提供替代方案。我们观察到，由于伪标签存在噪声，现有方法在数据稀疏度较高时性能会受到影响。为避免这一问题，我们提出一种端到端系统，该系统通过伪正例挖掘，学习将候选区域划分为已标注区域和未标注区域。已标注区域按常规方式处理，而未标注区域则采用自监督学习进行处理，从而避免噪声伪标签带来的负面影响。这种新颖方法具备多重优势，例如与现有方法相比，对更高稀疏度的鲁棒性更强。我们在PASCAL-VOC和COCO数据集的五个数据划分上开展了详尽实验，取得了当前最优性能。我们还统一了现有文献中用于该任务的各类数据划分，并提出了一个标准化基准。在COCO数据集上三个稀疏度递增的划分中，我们的方法相较于此前的最优方法，平均mAP分别提升了$2.6$、$3.9$和$9.6$。我们的项目公开发布于https://www.cs.umd.edu/~sakshams/SparseDet。
英文摘要：
Training with sparse annotations is known to reduce the performance of object detectors. Previous methods have focused on proxies for missing ground truth annotations in the form of pseudo-labels for unlabeled boxes. We observe that existing methods suffer at higher levels of sparsity in the data due to noisy pseudo-labels. To prevent this, we propose an end-to-end system that learns to separate the proposals into labeled and unlabeled regions using Pseudo-positive mining. While the labeled regions are processed as usual, self-supervised learning is used to process the unlabeled regions thereby preventing the negative effects of noisy pseudo-labels. This novel approach has multiple advantages such as improved robustness to higher sparsity when compared to existing methods. We conduct exhaustive experiments on five splits on the PASCAL-VOC and COCO datasets achieving state-of-the-art performance. We also unify various splits used across literature for this task and present a standardized benchmark. On average, we improve by $2.6$, $3.9$ and $9.6$ mAP over previous state-of-the-art methods on three splits of increasing sparsity on COCO. Our project is publicly available at https://www.cs.umd.edu/~sakshams/SparseDet.
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。
