论文标题
选择性卷积网络：一个有效的对象检测器，忽略背景
Selective Convolutional Network: An Efficient Object Detector with Ignoring Background
论文作者
论文摘要
众所周知，注意机制可以有效地改善包括对象探测器在内的许多CNN的性能。我们通过新颖的注意力尝试降低了过度的计算复杂性，而不是普遍地精炼特征地图。因此，我们引入了一个称为选择性卷积网络（SCN）的有效对象检测器，该对象检测器仅在包含有意义和有益信息的位置选择性计算。基本思想是排除微不足道的背景区域，这有效地降低了计算成本，尤其是在功能提取过程中。为了解决它，我们设计了一个精心设计的结构，其间接费用可忽略不计，以指导网络接下来的位置。它是端到端的可训练且易于装饰的。没有其他分割数据集，我们将探讨两种不同的火车策略，包括直接监督和间接监督。广泛的实验评估了Pascal VOC2007和MS可可检测数据集的性能。结果表明，SSD和PELEE与我们的方法集成在一起，通常将计算在1/5和1/3的范围内降低，精确度略有损失，这表明SCN的可行性。
It is well known that attention mechanisms can effectively improve the performance of many CNNs including object detectors. Instead of refining feature maps prevalently, we reduce the prohibitive computational complexity by a novel attempt at attention. Therefore, we introduce an efficient object detector called Selective Convolutional Network (SCN), which selectively calculates only on the locations that contain meaningful and conducive information. The basic idea is to exclude the insignificant background areas, which effectively reduces the computational cost especially during the feature extraction. To solve it, we design an elaborate structure with negligible overheads to guide the network where to look next. It's end-to-end trainable and easy-embedding. Without additional segmentation datasets, we explores two different train strategies including direct supervision and indirect supervision. Extensive experiments assess the performance on PASCAL VOC2007 and MS COCO detection datasets. Results show that SSD and Pelee integrated with our method averagely reduce the calculations in a range of 1/5 and 1/3 with slight loss of accuracy, demonstrating the feasibility of SCN.
