论文标题
基于区域建议的对象探测器的混合正则化
Mixup Regularization for Region Proposal based Object Detectors
论文作者
论文摘要
混音 - 一种基于标记样品对的线性插值的神经网络正则化技术 - 它的能力取决于其通过令人惊讶的简单形式主义提高模型的鲁棒性和概括性的能力。但是，由于不能天真地定义边界框的插值，因此其扩展到对象检测场仍然不清楚。在本文中，我们建议利用锚固的固有区域映射结构，以引入基于区域建议对象检测器的混合驱动训练正则化。提出的方法在具有挑战性检测设置的标准数据集上进行了基准测试。我们的实验表明，图像变化的鲁棒性增强，并具有将检测删除的能力，从而提高了概括能力。
Mixup - a neural network regularization technique based on linear interpolation of labeled sample pairs - has stood out by its capacity to improve model's robustness and generalizability through a surprisingly simple formalism. However, its extension to the field of object detection remains unclear as the interpolation of bounding boxes cannot be naively defined. In this paper, we propose to leverage the inherent region mapping structure of anchors to introduce a mixup-driven training regularization for region proposal based object detectors. The proposed method is benchmarked on standard datasets with challenging detection settings. Our experiments show an enhanced robustness to image alterations along with an ability to decontextualize detections, resulting in an improved generalization power.
