TY - Jour A2 - 王,彭威奥卢 - 他,救生奥江,明澳 - Ohbuchi,Ryutarou Au - Furuya,Takahiko Au - Zhang,Min Au - Li,Pengfei Py - 2020 da - 2020/12/22 ti -SCALE Adaptive Feature金字塔网络用于2D对象检测SP - 8839979 VL - 2020 AB - 对象检测是计算机视觉中的核心任务之一。对象检测算法通常难以检测具有不同尺度的对象,尤其是具有较小尺寸的对象。应对这个问题,林等。建议的特征金字塔网络(FPN),其目的是每个比例级别的特征金字塔,具有更高的语义内容。FPN包括自下而上的金字塔和自上而下的金字塔。卷积神经网络诱导自下而上的金字塔作为其特征图的层。通过逐步上抽样在自下而上的金字塔顶部的高度语义且低分辨率特征映射的渐进式上采样来形成自上而下的金字塔。在每个上抽样步骤中,自下而上金字塔的特征映射与自上而下的金字塔融合,以在自上而下的金字塔中产生高度语义但高分辨率的特征映射。尽管有重大改进,但FPN仍然错过了小规模的物体。 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. SN - 1058-9244 UR - https://doi.org/10.1155/2020/8839979 DO - 10.1155/2020/8839979 JF - Scientific Programming PB - Hindawi KW - ER -