论文标题
HRDNET：小对象的高分辨率检测网络
HRDNet: High-resolution Detection Network for Small Objects
论文作者
论文摘要
小对象检测具有挑战性，因为小对象不包含详细信息，甚至可能在深网中消失。通常，将高分辨率图像馈送到网络中可以减轻此问题。但是，仅仅扩大分辨率将引起更多问题，例如，它加剧了对象尺度的大型变体，并引入了难以忍受的计算成本。为了保持高分辨率图像的好处而没有提出新问题，我们提出了高分辨率检测网络（HRDNET）。 HRDNET使用多深度骨干进行多个分辨率输入。为了充分利用多个功能，我们提出了HRDNET中的多深度图像金字塔网络（MD-IPN）和多尺度特征金字塔网络（MS-FPN）。 MD-IPN使用多个深度骨架维护多个位置信息。具体而言，高分辨率输入将被送入一个浅网络，以保留更多的位置信息并降低计算成本，而低分辨率输入将被馈入深层网络以提取更多的语义。通过从高分辨率到低分辨率提取各种功能，MD-IPN能够提高小物体检测的性能，并保持中间和大对象的性能。提出MS-FPN来对齐和融合由MD-IPN生成的多尺度特征组，以减少这些多尺度多级特征之间的信息不平衡。在标准基准数据集上进行了广泛的实验和消融研究，MS COCO2017，PASCAL VOC2007/2012和典型的小对象数据集，Visdrone 2019。尤其是，我们提出的HRDNET可以在这些数据集上实现最新的ART，并在这些数据集上进行更好的作用。
Small object detection is challenging because small objects do not contain detailed information and may even disappear in the deep network. Usually, feeding high-resolution images into a network can alleviate this issue. However, simply enlarging the resolution will cause more problems, such as that, it aggravates the large variant of object scale and introduces unbearable computation cost. To keep the benefits of high-resolution images without bringing up new problems, we proposed the High-Resolution Detection Network (HRDNet). HRDNet takes multiple resolution inputs using multi-depth backbones. To fully take advantage of multiple features, we proposed Multi-Depth Image Pyramid Network (MD-IPN) and Multi-Scale Feature Pyramid Network (MS-FPN) in HRDNet. MD-IPN maintains multiple position information using multiple depth backbones. Specifically, high-resolution input will be fed into a shallow network to reserve more positional information and reducing the computational cost while low-resolution input will be fed into a deep network to extract more semantics. By extracting various features from high to low resolutions, the MD-IPN is able to improve the performance of small object detection as well as maintaining the performance of middle and large objects. MS-FPN is proposed to align and fuse multi-scale feature groups generated by MD-IPN to reduce the information imbalance between these multi-scale multi-level features. Extensive experiments and ablation studies are conducted on the standard benchmark dataset MS COCO2017, Pascal VOC2007/2012 and a typical small object dataset, VisDrone 2019. Notably, our proposed HRDNet achieves the state-of-the-art on these datasets and it performs better on small objects.
