It is a consensus that feature maps in the shallow layer are more related to image attributes such as texture and shape, whereas abstract semantic representation exists in the deep layer. Meanwhile, some image information will be lost in the process of the convolution operation. Naturally, the direct method is combining them together to gain lost detailed information through concatenation or adding. In fact, the image representation flowed in feature fusion can not match with the semantic representation completely, and the semantic deviation in different layers also destroy the information purification, that leads to useless information being mixed into the fusion layers. Therefore, it is crucial to narrow the gap among the fused layers and reduce the impact of noises during fusion. In this paper, we propose a method named weight mechanism to reduce the gap between feature maps in concatenation of series connection, and we get a better result of 0.80% mIoU improvement on Massachusetts building dataset by changing the weight of the concatenation of series connection in residual U-Net. Specifically, we design a new architecture named fused U-Net to test weight mechanism, and it also gains 0.12% mIoU improvement.
翻译:一种共识是,浅层地图的特征更多地与图质和形状等图像属性有关,而抽象的语义表示则存在于深层层中。 同时,一些图像信息在卷动操作过程中会丢失。 自然, 直接的方法是将图像信息合并在一起, 以便通过连接或添加获得丢失的详细信息。 事实上, 特征混合中的图像表达方式不能完全与语义表达方式相匹配, 不同层的语义偏差也会破坏信息净化, 从而导致将无用信息混入聚合层。 因此, 关键是缩小连接层之间的差距, 减少聚变过程中噪音的影响。 在本文中, 我们提出了一个命名为权重机制的方法, 以缩小组合序列连接中地貌地图之间的差距。 我们通过改变剩余 U- Net 中序列连接的权重来改善麻省建筑数据集。 具体地说, 我们设计了一个名为 U- Net 集成 U- 测试重量机制的新结构, 也取得了0. 12% mIOU 的改进。