The large kernel (and effective receptive field) plays an important role when we have to perform the classification and localization tasks simultaneously.（当我们必须同时执行分类和定位任务时，大内核（和有效的感知野）起着重要作用）
we propose a Global Convolutional Network to address both the classification and localization issues for the semantic segmentation.（提出GCN来解决语义分割的分类和定位问题）
We also suggest a residual-based boundary refinement to further refine the object boundaries.（基于残差的边界细化以进一步细化目标边界）
82.2% (vs 80.2%) on PASCAL VOC 2012 dataset and 76.9% (vs 71.8%) on Cityscapes dataset.
-
引言
For the classification task, the models are required to be invariant to various transformations like translation and rotation. But for the localization task, models should be transformation-sensitive -
方法
First from the localization view, the structure must be fully-convolutional without any fully-connected layer or global pooling layer that used by many classification networks, since the latter will discard localization information. Second from the classification view, motivated by the densely-connected structure of classification models, the kernel size of the convolutional structure should be as large as possible.
GCN module employs a combination of 1 x k + k x 1 and k x 1 + 1 x k convolutions, which enables densely connections within a large k x k region in the feature map，we do not use any nonlinearity after convolution layers.we models the boundary alignment as a residual structure.S = S + R（S）,where S is
the coarse score map and R() is the residual branch.
3. 实验
We evaluate our approach on the standard benchmark PASCAL VOC 2012 [11, 10] and Cityscapes [8]. PASCAL VOC 2012 has 1464 images for training, 1449 images for validation and 1456 images for testing, which belongs to 20 object classes along with one background class. We also use the Semantic Boundaries Dataset [13] as auxiliary dataset, resulting in 10,582 images for training. We choose the state-of-the-art network ResNet 152 [14] (pretrained on ImageNet [28]) as our base model for fine tuning. During the training time, we use standard SGD [20] with batch size 1, momentum 0.99 and weight decay 0.0005 . Data augmentations like mean subtraction and horizontal flip are also applied in training.
we pad each input image into 512 x 512 so that the top-most feature map is 16 x 16.
Only odd size are used just to avoid alignment error.(k值)（k值的范围可根据最后一个特征图的大小来定）
虽然GCN的网络结构增加了参数量，但是通过与实验C进行对比证明了性能的提升并不是因为参数量的增加。
GCN模型主要提高了内部区域的准确性，而边界区域的影响较小（大型物体中心的像素+GCN≈“纯”分类问题）