This paper proposes a novel attention model for semantic segmentation, which
aggregates multi-scale and context features to refine prediction. Specifically,
the skeleton convolutional neural network framework takes in multiple different
scales inputs, by which means the CNN can get representations in different
scales. The proposed attention model will handle the features from different
scale streams respectively and integrate them. Then location attention branch
of the model learns to softly weight the multi-scale features at each pixel
location. Moreover, we add an recalibrating branch, parallel to where location
attention comes out, to recalibrate the score map per class. We achieve quite
competitive results on PASCAL VOC 2012 and ADE20K datasets, which surpass
baseline and related works.

本文提出了一种新颖的注视模型用于语义分割，该模型聚合了多尺度和上下文特征进行预测。该模型使用骨骼卷积神经网络框架输入多个不同的尺度，进而可以获取不同尺度的表示。提出的注视模型将分别处理不同尺度的特征并集成它们。然后，该模型的位置注视分支学习到每个像素位置上的多尺度特征的软加权。此外，我们添加了一个重新校准分支，与位置注视分支平行，用于重新校准每个类别的分数图。在 PASCAL VOC 2012 和 ADE20K 数据集上，我们取得了相当有竞争力的结果，超过了基线和相关工作。