论文标题
CPM R-CNN：对象检测中的校准指引导的未对准
CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection
论文作者
论文摘要
在对象检测中，偏移引导和指导的回归分别占据基于锚的和无锚的方法。最近，将指导的方法引入了基于锚的方法。但是，我们观察到以这种方式预测的点与匹配的建议区域和本地化得分未对准，从而导致了显着的绩效差距。在本文中，我们提出了CPM R-CNN，其中包含三个有效的模块，以优化基于锚的点指导方法。根据对可可数据集的足够评估，CPM R-CNN被证明有效地通过校准上述未对准来提高定位准确性。与基于FPN的RESNET-101基于RESNET-101的更快的R-CNN和GRID R-CNN相比，我们的方法基本上可以将检测图分别提高3.3％和1.5％，而无需哨声和铃铛。此外，我们的最佳模型在可可测试dev方面可获得很大的利润率，达到49.9％。代码和模型将公开可用。
In object detection, offset-guided and point-guided regression dominate anchor-based and anchor-free method separately. Recently, point-guided approach is introduced to anchor-based method. However, we observe points predicted by this way are misaligned with matched region of proposals and score of localization, causing a notable gap in performance. In this paper, we propose CPM R-CNN which contains three efficient modules to optimize anchor-based point-guided method. According to sufficient evaluations on the COCO dataset, CPM R-CNN is demonstrated efficient to improve the localization accuracy by calibrating mentioned misalignment. Compared with Faster R-CNN and Grid R-CNN based on ResNet-101 with FPN, our approach can substantially improve detection mAP by 3.3% and 1.5% respectively without whistles and bells. Moreover, our best model achieves improvement by a large margin to 49.9% on COCO test-dev. Code and models will be publicly available.
