Scale Adaptive Feature Pyramid Networks for 2D Object Detection
Scale Adaptive Feature Pyramid Networks for 2D Object Detection
复制标题
用于 2D 物体检测的尺度自适应特征金字塔网络
DOI：
10.1155/2020/8839979
复制
发表时间：
2020
影响因子：
--
通讯作者：
Li Pengfei
中科院分区：
文献类型：
--
作者：
He Lifei;Jiang Ming;Ohbuchi Ryutarou;Furuya Takahiko;Zhang Min;Li Pengfei
目标检测是计算机视觉的核心任务之一。对象检测算法通常难以检测具有不同尺度的对象，尤其是具有较小尺度的对象。为了科普这个问题，Lin等人提出了特征金字塔网络（FPN），其目标是在每个尺度级别上具有更高语义内容的特征金字塔。FPN由一个自下而上的金字塔和一个自上而下的金字塔组成。自下而上的金字塔由卷积神经网络诱导作为其特征映射层。自上而下金字塔是通过在自下而上金字塔的顶部对高语义但低分辨率的特征图进行渐进式上采样而形成的。在每个上采样步骤中，自下而上金字塔的特征图与自上而下金字塔融合，以在自上而下金字塔中生成高度语义但高分辨率的特征图。尽管有显著的改进，FPN仍然错过了小尺度对象。为了进一步提高小尺度物体的检测能力，本文提出了尺度自适应特征金字塔网络（SAFPNs）。SAFPN在融合自底向上金字塔和自顶向下金字塔的特征图时采用自适应选择的每个输入图像的权重。尺度自适应权重的计算，通过使用一个规模注意模块内置到特征地图融合计算。缩放注意力模块是端到端训练的，以适应训练数据集的图像中包含的对象的缩放。使用2阶段检测器更快的R-CNN和1阶段检测器RetinaNet的实验评估证明了所提出的方法的有效性。
Object detection is one of the core tasks in computer vision. Object detection algorithms often have difficulty detecting objects with diverse scales, especially those with smaller scales. To cope with this issue, Lin et al. proposed feature pyramid networks (FPNs), which aim for a feature pyramid with higher semantic content at every scale level. The FPN consists of a bottom‐up pyramid and a top‐down pyramid. The bottom‐up pyramid is induced by a convolutional neural network as its layers of feature maps. The top‐down pyramid is formed by progressive up‐sampling of a highly semantic yet low‐resolution feature map at the top of the bottom‐up pyramid. At each up‐sampling step, feature maps of the bottom‐up pyramid are fused with the top‐down pyramid to produce highly semantic yet high‐resolution feature maps in the top‐down pyramid. Despite significant improvement, the FPN still misses small‐scale objects. To further improve the detection of small‐scale objects, this paper proposes scale adaptive feature pyramid networks (SAFPNs). The SAFPN employs weights chosen adaptively to each input image in fusing feature maps of the bottom‐up pyramid and top‐down pyramid. Scale adaptive weights are computed by using a scale attention module built into the feature map fusion computation. The scale attention module is trained end‐to‐end to adapt to the scale of objects contained in images of the training dataset. Experimental evaluation, using both the 2‐stage detector faster R‐CNN and 1‐stage detector RetinaNet, demonstrated the proposed approach’s effectiveness.
DOI：
10.1109/tpami.2016.2577031
发表时间：
2017-06-01
影响因子：
23.6
作者：
Ren, Shaoqing;He, Kaiming;Sun, Jian
通讯作者：
Sun, Jian