Semantic segmentation tasks can be well modeled by Markov Random Field (MRF). This paper addresses semantic segmentation by incorporating high-order relations and mixture of label contexts into MRF. Unlike previous works that optimized MRFs using iterative algorithm, we solve MRF by proposing a Convolutional Neural Network (CNN), namely Deep Parsing Network (DPN), which enables deterministic end-to-end computation in a single forward pass. Specifically, DPN extends a contemporary CNN to model unary terms and additional layers are devised to approximate the mean field (MF) algorithm for pairwise terms. It has several appealing properties. First, different from the recent works that required many iterations of MF during back-propagation, DPN is able to achieve high performance by approximating one iteration of MF. Second, DPN represents various types of pairwise terms, making many existing models as its special cases. Furthermore, pairwise terms in DPN provide a unified framework to encode rich contextual information in high-dimensional data, such as images and videos. Third, DPN makes MF easier to be parallelized and speeded up, thus enabling efficient inference. DPN is thoroughly evaluated on standard semantic image/video segmentation benchmarks, where a single DPN model yields state-of-the-art segmentation accuracies on PASCAL VOC 2012, Cityscapes dataset and CamVid dataset.

中文翻译：

---

用于语义分割的深度学习马尔可夫随机场


语义分割任务可以通过马尔可夫随机场（MRF）很好地建模。本文通过将高阶关系和标签上下文混合合并到 MRF 中来解决语义分割问题。与之前使用迭代算法优化 MRF 的工作不同，我们通过提出卷积神经网络（CNN），即深度解析网络（DPN）来解决 MRF，它可以在单次前向传递中实现确定性端到端计算。具体来说，DPN 扩展了当代 CNN 来对一元项进行建模，并设计了附加层来近似成对项的平均场 (MF) 算法。它有几个吸引人的特性。首先，与最近的在反向传播过程中需要多次迭代 MF 的工作不同，DPN 能够通过逼近 MF 的一次迭代来实现高性能。其次，DPN 表示各种类型的成对项，使许多现有模型成为其特例。此外，DPN 中的成对项提供了一个统一的框架来编码高维数据（例如图像和视频）中的丰富上下文信息。第三，DPN使得MF更容易并行化和加速，从而实现高效的推理。 DPN 在标准语义图像/视频分割基准上进行了全面评估，其中单个 DPN 模型在 PASCAL VOC 2012、Cityscapes 数据集和 CamVid 数据集上产生了最先进的分割精度。