具有整流IoU损耗的单次双叉探测器
Single-Shot Two-Pronged Detector with Rectified IoU Loss
摘要：
在基于CNN的对象检测器中，特征金字塔被广泛利用来缓解对象实例之间的尺度变化的问题。这些对象检测器通过自上而下的路径和横向连接来增强特征，主要是为了丰富低层特征的语义信息，而忽略了高层特征的增强。这可能导致不同层次特征之间的不平衡，特别是高级特征中严重缺乏详细信息，这使得难以获得准确的边界框。本文提出了一种新的双向转换思想，从前后两个方向探索不同层次之间的关系，既丰富了低层特征的语义信息，又丰富了高层特征的细节信息。在这一双管齐下的思想指导下，本文提出了一种双叉网络（Two-Pronged Network，TPNet），实现了高层特征和底层特征的双向传递，有助于在不同尺度下准确检测目标。此外，由于单级检测器中难样本和易样本之间的分布不平衡，定位损失的梯度总是由定位精度较差的难样本主导。这将使模型偏向硬样本。因此，在我们的TPNet中，提出了一种自适应的基于IoU的定位损失，称为矫正IoU（RIoU）损失，以纠正每种样本的梯度。修正后的IoU损失增加了高IoU样本的梯度，同时抑制了低IoU样本的梯度，这可以提高模型的整体定位精度。大量的实验证明了我们的TPNet和RIoU损失的优越性。
英文摘要：
In the CNN based object detectors, feature pyramids are widely exploited to alleviate the problem of scale variation across object instances. These object detectors, which strengthen features via a top-down pathway and lateral connections, are mainly to enrich the semantic information of low-level features, but ignore the enhancement of high-level features. This can lead to an imbalance between different levels of features, in particular a serious lack of detailed information in the high-level features, which makes it difficult to get accurate bounding boxes. In this paper, we introduce a novel two-pronged transductive idea to explore the relationship among different layers in both backward and forward directions, which can enrich the semantic information of low-level features and detailed information of high-level features at the same time. Under the guidance of the two-pronged idea, we propose a Two-Pronged Network (TPNet) to achieve bidirectional transfer between high-level features and low-level features, which is useful for accurately detecting object at different scales. Furthermore, due to the distribution imbalance between the hard and easy samples in single-stage detectors, the gradient of localization loss is always dominated by the hard examples that have poor localization accuracy. This will enable the model to be biased toward the hard samples. So in our TPNet, an adaptive IoU based localization loss, named Rectified IoU (RIoU) loss, is proposed to rectify the gradients of each kind of samples. The Rectified IoU loss increases the gradients of examples with high IoU while suppressing the gradients of examples with low IoU, which can improve the overall localization accuracy of model. Extensive experiments demonstrate the superiority of our TPNet and RIoU loss.
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。
