SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection
SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection
复制标题
DOI：
10.1007/978-3-030-01228-1_20
复制
发表时间：
2018-08
期刊：
影响因子：
--
通讯作者：
Y. Kim;Bong-Nam Kang;Daijin Kim
中科院分区：
文献类型：
--
作者：
Y. Kim;Bong-Nam Kang;Daijin Kim
最近在精确目标检测方面的大多数成功方法都建立在卷积神经网络(CNN)的基础上。然而，由于基于CNN的检测方法缺乏尺度归一化，使得特征空间中激活的通道可能根据尺度的不同而完全不同，这种差异使得分类器很难学习样本。提出了一种尺度感知网络(SAN)，将不同尺度的卷积特征映射到尺度不变子空间，使基于CNN的检测方法对尺度变化具有更强的鲁棒性，并构造了一种独特的学习方法，该方法仅考虑通道之间的关系，而不考虑空间信息，从而实现了SAN的高效学习。为了证明该方法的有效性，我们通过一个通道激活矩阵来可视化卷积特征是如何随尺度变化的，并通过实验证明了SAN减小了尺度空间中的特征差异。我们在VOC、PASCAL和MS COCO数据集上对我们的方法进行了评估。我们通过几个关于结构和参数的实验来演示SAN。该算法可广泛应用于多种基于CNN的检测方法中，在略微增加计算时间的情况下提高检测精度。
Most of the recent successful methods in accurate object detection build on the convolutional neural networks (CNN). However, due to the lack of scale normalization in CNN-based detection methods, the activated channels in the feature space can be completely different according to a scale and this difference makes it hard for the classifier to learn samples. We propose a Scale Aware Network (SAN) that maps the convolutional features from the different scales onto a scale-invariant subspace to make CNN-based detection methods more robust to the scale variation, and also construct a unique learning method which considers purely the relationship between channels without the spatial information for the efficient learning of SAN. To show the validity of our method, we visualize how convolutional features change according to the scale through a channel activation matrix and experimentally show that SAN reduces the feature differences in the scale space. We evaluate our method on VOC PASCAL and MS COCO dataset. We demonstrate SAN by conducting several experiments on structures and parameters. The proposed SAN can be generally applied to many CNN-based detection methods to enhance the detection accuracy with a slight increase in the computing time.