Propose-and-Attend Single Shot Detector
Propose-and-Attend Single Shot Detector
复制标题
DOI：
10.1109/wacv45572.2020.9093364
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
Hoyong Jang;Sanghyun Woo;Philipp Benz;Jinsun Park;I. Kweon
中科院分区：
文献类型：
--
作者：
Hoyong Jang;Sanghyun Woo;Philipp Benz;Jinsun Park;I. Kweon
我们为单级检测器提出了一种简单而有效的预测模块。主要工序是由粗到细进行的。首先，该模块粗略地调整默认框以更好地捕获图像中目标对象的范围。其次，给定调整后的框，该模块相应地对齐卷积滤波器的感受野，而不需要任何嵌入层。这两个步骤都构建了提议并出席机制，以高效的方式模仿两级检测器。为了验证其有效性，我们将所提出的模块应用于基本的单级检测器 SSD。我们凭经验表明，我们的模块以边际参数开销显着提高了检测精度。我们的最终模型达到了与最先进的检测器相当的精度，同时使用了其模型参数和计算开销的一小部分。此外，我们发现所提出的模块有两个强大的应用程序。 1）该模块可以成功集成到轻量级主干中，进一步提升一级探测器的效率。 2) 该模块还允许从头开始训练，而无需像以前的方法那样依赖任何复杂的基础网络。
We present a simple yet effective prediction module for a one-stage detector. The main process is conducted in a coarse-to-fine manner. First, the module roughly adjusts the default boxes to well capture the extent of target objects in an image. Second, given the adjusted boxes, the module aligns the receptive field of the convolution filters accordingly, not requiring any embedding layers. Both steps build a propose-and-attend mechanism, mimicking two-stage detectors in a highly efficient manner. To verify its effectiveness, we apply the proposed module to a basic one-stage detector SSD. We empirically show that our module significantly lifts the detection accuracy with marginal parameter overhead. Our final model achieves an accuracy comparable to that of state-of-the-art detectors while using a fraction of their model parameter and computational overheads. Moreover, we found that the proposed module has two strong applications. 1) The module can be successfully integrated into a lightweight backbone, further pushing the efficiency of the one-stage detector. 2) The module also allows train-from-scratch without relying on any sophisticated base networks as previous methods do.