论文标题
替换block：基于背景信息的改进的正则化方法
ReplaceBlock: An improved regularization method based on background information
论文作者
论文摘要
注意机制经常用于训练网络以获得更好的特征表示，可以有效地将目标对象与背景中无关的对象脱离。给定任意图像，我们发现背景的无关物体最有可能阻塞/阻止目标对象。我们根据这一发现提出了一个替换池，以模拟目标对象被视为背景的对象部分遮住时。具体而言，替换板删除图像中的目标对象，然后仅通过模型与无关的对象和背景生成特征映射。最后，背景特征映射中的某些区域用于替换原始图像特征映射中目标对象的某些区域。这样，替换板可以有效地模拟遮挡图像的特征图。实验结果表明，在正规化卷积网络中，替换板比Dropblock效果更好。
Attention mechanism, being frequently used to train networks for better feature representations, can effectively disentangle the target object from irrelevant objects in the background. Given an arbitrary image, we find that the background's irrelevant objects are most likely to occlude/block the target object. We propose, based on this finding, a ReplaceBlock to simulate the situations when the target object is partially occluded by the objects that are deemed as background. Specifically, ReplaceBlock erases the target object in the image, and then generates a feature map with only irrelevant objects and background by the model. Finally, some regions in the background feature map are used to replace some regions of the target object in the original image feature map. In this way, ReplaceBlock can effectively simulate the feature map of the occluded image. The experimental results show that ReplaceBlock works better than DropBlock in regularizing convolutional networks.
